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

    Neuronpedia

    INDEX
    Explanations

    charge

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Europ
    -0.07
     occupants
    -0.06
     Derm
    -0.06
     opción
    -0.06
     poprvé
    -0.06
     mutex
    -0.06
    ierz
    -0.06
    logged
    -0.06
    _ind
    -0.06
     denied
    -0.06
    POSITIVE LOGITS
     wyn
    0.07
     coy
    0.07
    승
    0.07
     adap
    0.06
    uben
    0.06
     chords
    0.06
    taient
    0.06
     Sms
    0.06
    =${
    0.06
     adı
    0.06
    Act Density 0.004%

    No Known Activations