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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Products
    -0.06
    _metrics
    -0.06
    -forward
    -0.06
     Georgetown
    -0.05
     Generates
    -0.05
    Temporal
    -0.05
     전용
    -0.05
    Reason
    -0.05
    upid
    -0.05
     Investors
    -0.05
    POSITIVE LOGITS
     مرتب
    0.08
     zam
    0.07
    deque
    0.07
    nee
    0.07
    _SWAP
    0.07
    coord
    0.06
    .Ar
    0.06
     prostituer
    0.06
    uencia
    0.06
    (hdc
    0.06
    Act Density 0.042%

    No Known Activations