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

    Neuronpedia

    INDEX
    Explanations

    math calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Boo
    -0.06
    keyCode
    -0.06
    Token
    -0.06
     ivory
    -0.06
     возрасте
    -0.06
     ambassador
    -0.06
    -language
    -0.06
     RG
    -0.06
    _from
    -0.06
     "))↵
    -0.06
    POSITIVE LOGITS
     combustion
    0.07
    [min
    0.06
     leagues
    0.06
     suburbs
    0.06
     超
    0.06
    chied
    0.06
    ASI
    0.06
     encuent
    0.06
    }-
    0.06
     correctness
    0.06
    Act Density 0.013%

    No Known Activations