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

    Neuronpedia

    INDEX
    Explanations

    Code or data snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quadr
    -0.07
     sixth
    -0.07
     분석
    -0.06
    ुख
    -0.06
     betrayal
    -0.06
     LAW
    -0.06
     mounts
    -0.06
    KeyPressed
    -0.06
     payouts
    -0.06
     Indones
    -0.06
    POSITIVE LOGITS
     南
    0.07
    mean
    0.06
    .volley
    0.06
    (effect
    0.06
    olit
    0.06
    입
    0.06
     Exact
    0.06
    _definition
    0.06
    Marketing
    0.06
     ecological
    0.06
    Act Density 0.000%

    No Known Activations