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

    Neuronpedia

    INDEX
    Explanations

    XML build files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    these
    -0.08
    糕
    -0.07
    增设
    -0.07
    �
    -0.07
    保罗
    -0.06
     könnt
    -0.06
    协会
    -0.06
     Be
    -0.06
     Certain
    -0.06
     vp
    -0.06
    POSITIVE LOGITS
    똥
    0.08
    BackingField
    0.07
    عالج
    0.07
    Utc
    0.07
    ław
    0.07
    PopMatrix
    0.06
    面积
    0.06
    ayscale
    0.06
    unks
    0.06
    ilogue
    0.06
    Act Density 0.007%

    No Known Activations