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

    Neuronpedia

    INDEX
    Explanations

    Positive personal statements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _DAYS
    -0.07
     místo
    -0.07
    prefs
    -0.06
    rides
    -0.06
    řez
    -0.06
    Cómo
    -0.06
     не
    -0.06
    Restricted
    -0.06
    acter
    -0.06
     whitelist
    -0.06
    POSITIVE LOGITS
     άλ
    0.06
    "`↵↵
    0.06
     SESSION
    0.06
     continue
    0.06
     supers
    0.06
     fim
    0.06
     Torah
    0.06
    -self
    0.06
     σκ
    0.06
    ген
    0.06
    Act Density 0.045%

    No Known Activations