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

    Neuronpedia

    INDEX
    Explanations

    quotient

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ffect
    -0.08
    	the
    -0.07
    fl
    -0.07
    VIC
    -0.07
    mit
    -0.07
    isable
    -0.07
     ")");↵
    -0.07
    loth
    -0.06
    ight
    -0.06
    represent
    -0.06
    POSITIVE LOGITS
    块钱
    0.08
    ומב
    0.08
     Babies
    0.08
    .ToolStripItem
    0.07
    _HOUR
    0.07
    .GetById
    0.07
    万公里
    0.07
     LIFE
    0.07
     поп
    0.07
     nắm
    0.07
    Act Density 0.022%

    No Known Activations