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

    Neuronpedia

    INDEX
    Explanations

    stantial

    np_max-act · gemini-2.0-flash

    The neuron activates on the phrase “circumstantial evidence” (and its variants), flagging mentions of evidence based on inference rather than direct proof.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Gan
    -0.06
    .boost
    -0.06
     rewind
    -0.06
    _pic
    -0.06
    _AUD
    -0.06
    _sql
    -0.06
     bereits
    -0.06
    cé
    -0.06
     dù
    -0.06
    .NotNull
    -0.06
    POSITIVE LOGITS
    оров
    0.07
    pector
    0.07
    атков
    0.06
     royalty
    0.06
     trục
    0.06
    母亲
    0.06
     سریع
    0.06
    _conditions
    0.06
    (right
    0.06
     survivors
    0.06
    Act Density 0.001%

    No Known Activations