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

    Neuronpedia

    INDEX
    Explanations

    Past/Present tenses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    QA
    -0.06
    Exactly
    -0.06
     sweating
    -0.06
    cury
    -0.06
    431
    -0.06
    _system
    -0.06
    áticas
    -0.06
     Beetle
    -0.06
     frü
    -0.06
     ku
    -0.06
    POSITIVE LOGITS
     відмов
    0.07
     disabling
    0.07
    olls
    0.07
    MISS
    0.06
    reibung
    0.06
     ));
    0.06
     poison
    0.06
    IRT
    0.06
     decorate
    0.06
    ml
    0.06
    Act Density 0.007%

    No Known Activations