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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =*
    -0.08
     Standards
    -0.07
    SID
    -0.07
    (XML
    -0.07
    (Calendar
    -0.07
    민
    -0.06
    aklı
    -0.06
    /interfaces
    -0.06
     inspirational
    -0.06
     minorities
    -0.06
    POSITIVE LOGITS
    _but
    0.07
    would
    0.07
    _GAME
    0.06
     piece
    0.06
     champs
    0.06
    ...');↵
    0.06
    —you
    0.06
    auge
    0.06
     expended
    0.06
     Carrie
    0.06
    Act Density 0.039%

    No Known Activations