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

    Neuronpedia

    INDEX
    Explanations

    Programming code/function calls

    np_max-act · gemini-2.0-flash

    issues related to programming and debugging in code.

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

    The neuron activates on numeric tokens or references to quantities (e.g. literal numbers, counts, or measurement values).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     separator
    -0.06
     Society
    -0.06
     ions
    -0.06
     Sala
    -0.06
    .localPosition
    -0.06
    �
    -0.06
     logos
    -0.06
    Lord
    -0.06
    qe
    -0.06
    ")(
    -0.06
    POSITIVE LOGITS
     Chain
    0.07
     inflated
    0.07
     Bands
    0.06
    .Syntax
    0.06
    剩
    0.06
    *g
    0.06
    _irq
    0.06
     Reduced
    0.06
    ُوا
    0.06
     racism
    0.06
    Act Density 0.213%

    No Known Activations