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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /gpio
    -0.07
     granted
    -0.07
    xAF
    -0.07
    én
    -0.07
     Negro
    -0.07
    Tmp
    -0.07
    骄
    -0.06
     ISIL
    -0.06
    olls
    -0.06
    REM
    -0.06
    POSITIVE LOGITS
    外援
    0.07
     слов
    0.07
     sonuç
    0.06
    .Reverse
    0.06
    申し込み
    0.06
    ('-',
    0.06
    -static
    0.06
    _lo
    0.06
     ^
    0.06
    inton
    0.06
    Act Density 0.001%

    No Known Activations