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

    Neuronpedia

    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash

    The neuron is detecting occurrences of the phrase “find out,” i.e. text signaling an information‐seeking or discovery construction.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    issors
    -0.07
     şeh
    -0.07
    Preferred
    -0.06
     caf
    -0.06
     fren
    -0.06
    388
    -0.06
     每
    -0.06
     nø
    -0.06
    (cpu
    -0.06
     смесь
    -0.06
    POSITIVE LOGITS
    В
    0.07
    -В
    0.06
     достав
    0.06
     HT
    0.06
     طبي
    0.06
    olog
    0.06
     legendary
    0.06
     regulator
    0.06
     stimulating
    0.06
    _receipt
    0.06
    Act Density 0.006%

    No Known Activations