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

    Neuronpedia

    INDEX
    Explanations

    algebraic simplification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Заг
    -0.07
    _xlabel
    -0.07
    isspace
    -0.07
     valore
    -0.06
     crashes
    -0.06
     Angela
    -0.06
     Kaz
    -0.06
    ourse
    -0.06
    ussion
    -0.06
    .xlabel
    -0.06
    POSITIVE LOGITS
     feather
    0.07
    849
    0.07
     Fur
    0.06
     hrd
    0.06
    085
    0.06
     Lâm
    0.06
    333
    0.06
     quy
    0.06
    Cİ
    0.06
     stirring
    0.06
    Act Density 0.004%

    No Known Activations