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

    Neuronpedia

    INDEX
    Explanations

    ad/Jad

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pathology
    -0.07
    _OPERATOR
    -0.07
    aviolet
    -0.07
    Chip
    -0.06
    ment
    -0.06
     zombie
    -0.06
     Bless
    -0.06
    xo
    -0.06
    estion
    -0.06
    丈
    -0.06
    POSITIVE LOGITS
    spě
    0.07
    ตล
    0.07
    ادي
    0.06
    特色
    0.06
    づ
    0.06
    مول
    0.06
     BACK
    0.06
    OLUMN
    0.06
     nuis
    0.06
    .deepcopy
    0.06
    Act Density 0.003%

    No Known Activations