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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .DEBUG
    -0.07
     Fo
    -0.06
     更
    -0.06
    －
    -0.06
    Ｌ
    -0.06
    无
    -0.06
     згод
    -0.06
     동
    -0.06
    此
    -0.06
     brom
    -0.06
    POSITIVE LOGITS
    .lastIndexOf
    0.06
     kid
    0.06
     gang
    0.06
    "struct
    0.06
     Damascus
    0.06
     docks
    0.06
    brace
    0.06
    ACHI
    0.06
     Cuando
    0.06
     Pablo
    0.06
    Act Density 0.001%

    No Known Activations