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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     viel
    -0.07
    品
    -0.07
    urized
    -0.07
    li
    -0.07
    bout
    -0.07
     predetermined
    -0.07
     fic
    -0.07
    hares
    -0.07
    _li
    -0.07
    سام
    -0.07
    POSITIVE LOGITS
     mathemat
    0.09
    formula
    0.09
    latex
    0.08
    ≈
    0.08
    <double
    0.08
     cálculo
    0.08
    @gmail
    0.08
     같습니다
    0.08
     Mathemat
    0.08
    នុ
    0.07
    Act Density 0.006%

    No Known Activations