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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    The neuron selectively fires on mentions of the opposing party (“defendant”) in legal‐case prose.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    bsites
    -0.07
    Dados
    -0.06
    .wait
    -0.06
     Dt
    -0.06
     Arap
    -0.06
    σι
    -0.06
    osit
    -0.06
    diler
    -0.06
    aoke
    -0.06
    cad
    -0.06
    POSITIVE LOGITS
    "",
    0.07
    _REPLY
    0.07
     Guerrero
    0.06
    ทำ
    0.06
     fictional
    0.06
    _TURN
    0.06
    Collider
    0.06
     contrasting
    0.06
    createView
    0.06
    (addr
    0.06
    Act Density 0.012%

    No Known Activations