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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,but
    -0.07
    én
    -0.07
    HEAD
    -0.07
    (io
    -0.07
    -spot
    -0.06
    "
    -0.06
    "
↵
    -0.06
    _editor
    -0.06
    iva
    -0.06
    CU
    -0.06
    POSITIVE LOGITS
     Uni
    0.07
     pharm
    0.06
    .Rem
    0.06
    Impossible
    0.06
    十八
    0.06
     CLIIIK
    0.06
     الاع
    0.06
    PageIndex
    0.06
    관계
    0.06
     sess
    0.06
    Act Density 0.000%

    No Known Activations