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

    Neuronpedia

    INDEX
    Explanations

    lig

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     значения
    -0.06
     Dropbox
    -0.06
    eken
    -0.06
    _unlock
    -0.06
     encuentra
    -0.06
     equally
    -0.06
     Cancel
    -0.06
     Clarkson
    -0.06
     archivo
    -0.05
    ССР
    -0.05
    POSITIVE LOGITS
     disruptive
    0.07
     bh
    0.07
    violent
    0.07
    cipher
    0.07
    止
    0.06
    0.06
     paramString
    0.06
     شهری
    0.06
    ρωπα
    0.06
     Disc
    0.06
    Act Density 0.002%

    No Known Activations