Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash

    configuration settings and options related to TypeScript compiler settings, particularly for module resolution.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires strongly on the double‐quote characters that begin JSON-style property names (i.e. quoted keys) in configuration blocks.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    rtype
    -0.07
    VectorXd
    -0.06
    르게
    -0.06
     teng
    -0.06
     foregoing
    -0.06
    �장
    -0.06
     strtol
    -0.06
     완
    -0.06
    may
    -0.06
     v�
    -0.06
    POSITIVE LOGITS
     disagree
    0.06
    weg
    0.06
     incentives
    0.06
     wiring
    0.06
    monkey
    0.06
     ranked
    0.06
    -num
    0.06
     stepped
    0.06
    84
    0.06
     crises
    0.06
    Act Density 0.005%

    No Known Activations