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

    Neuronpedia

    INDEX
    Explanations

    legal filings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _multiplier
    -0.07
     unlocked
    -0.07
     Week
    -0.06
    -part
    -0.06
    _long
    -0.06
     embedded
    -0.06
     свои
    -0.06
    mesinin
    -0.06
    atıcı
    -0.06
     kHz
    -0.06
    POSITIVE LOGITS
     prohibited
    0.07
    ?");↵
    0.07
     milfs
    0.06
     experi
    0.06
    уж
    0.06
    riters
    0.06
    =json
    0.06
     #@
    0.06
    Il
    0.06
     typically
    0.06
    Act Density 0.016%

    No Known Activations