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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dividend
    -0.09
    Marshal
    -0.09
     EBITDA
    -0.09
     Toda
    -0.08
    Dividend
    -0.08
    whose
    -0.08
    qan
    -0.08
    ğlu
    -0.08
     cad
    -0.08
    偿
    -0.07
    POSITIVE LOGITS
     ఎంప
    0.12
    选择
    0.12
    เลือก
    0.12
     combinations
    0.11
     sélection
    0.11
     combos
    0.11
     Auswahl
    0.11
     selects
    0.11
     선택
    0.11
     selections
    0.10
    Act Density 0.032%

    No Known Activations