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

    Neuronpedia

    INDEX
    Explanations

    1990s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    queryParams
    -0.07
    ROLE
    -0.07
    bps
    -0.07
     yandan
    -0.06
    PROP
    -0.06
    /callback
    -0.06
    truck
    -0.06
     silver
    -0.06
     Some
    -0.06
     Fox
    -0.06
    POSITIVE LOGITS
    communic
    0.08
    198
    0.07
     �
    0.07
    ۲۰۰
    0.06
    199
    0.06
     セ
    0.06
     літ
    0.06
    201
    0.06
    結
    0.06
     GCC
    0.06
    Act Density 0.013%

    No Known Activations