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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    غ
    -0.07
     dick
    -0.07
    REET
    -0.06
    .cbo
    -0.06
    icult
    -0.06
    港
    -0.06
     attraction
    -0.06
    .root
    -0.06
    ROWS
    -0.06
    政策
    -0.06
    POSITIVE LOGITS
    .za
    0.07
     людина
    0.06
    repeat
    0.06
    -equ
    0.06
    atype
    0.06
    Clip
    0.06
    _copy
    0.06
    Mes
    0.06
    ώντας
    0.06
     cocos
    0.06
    Act Density 0.030%

    No Known Activations