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

    Neuronpedia

    INDEX
    Explanations

    blackmail

    np_max-act · gemini-2.0-flash

    This neuron never responds to any input—it appears to be inactive or “dead.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .patch
    -0.07
     patch
    -0.07
     massively
    -0.07
    _patch
    -0.06
     الخ
    -0.06
    Relationship
    -0.06
     процесса
    -0.06
     Arnold
    -0.06
     が
    -0.06
    .Pages
    -0.06
    POSITIVE LOGITS
     coerce
    0.08
     intimid
    0.07
     intimidation
    0.07
     intrig
    0.07
    getInt
    0.06
    نز
    0.06
    imore
    0.06
     extortion
    0.06
    biz
    0.06
     Lucia
    0.06
    Act Density 0.009%

    No Known Activations