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

    Neuronpedia

    INDEX
    Explanations

    pointer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     clauses
    -0.07
    阶
    -0.07
    -suite
    -0.07
    -confidence
    -0.07
    _escape
    -0.07
    END
    -0.06
    Stub
    -0.06
    的经典
    -0.06
    窠
    -0.06
     Written
    -0.06
    POSITIVE LOGITS
    Ｔ
    0.08
     pela
    0.07
     lesbians
    0.07
     plywood
    0.07
     bitcoins
    0.07
     '\\'
    0.07
     Lily
    0.07
    lator
    0.07
    battery
    0.06
     iy
    0.06
    Act Density 0.001%

    No Known Activations