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

    Neuronpedia

    INDEX
    Explanations

    Development role/team

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     upgrading
    0.48
    seekers
    0.47
     traditional
    0.45
    atthaya
    0.44
    canceled
    0.44
     Utilizing
    0.44
     socializing
    0.43
    ated
    0.43
    s
    0.42
    rating
    0.41
    POSITIVE LOGITS
    دارة
    0.49
     errori
    0.49
     Fälle
    0.48
     Fehler
    0.48
     seuls
    0.47
     Spieler
    0.47
     malos
    0.47
     résultats
    0.46
     decisão
    0.46
     diseñado
    0.46
    Act Density 0.009%

    No Known Activations