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
    /GL
    -0.08
    侯
    -0.07
     Woj
    -0.07
     Expand
    -0.07
    =msg
    -0.06
     WAY
    -0.06
     Victim
    -0.06
     Successful
    -0.06
     substantial
    -0.06
    Ang
    -0.06
    POSITIVE LOGITS
     guint
    0.07
    Higher
    0.06
    (TokenType
    0.06
    xcd
    0.06
    일반
    0.06
    ґ
    0.06
    錢
    0.06
    Highest
    0.06
     高
    0.06
    DllImport
    0.06
    Act Density 0.003%

    No Known Activations