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

    Neuronpedia

    INDEX
    Explanations

    American Psycho, history, Android

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    少なくとも
    0.43
    というか
    0.43
    atsiooni
    0.42
    风格
    0.42
    ിലുള്ള
    0.41
     dice
    0.40
    のでしょうか
    0.40
     nudge
    0.40
     tomorrow
    0.39
    ത്തിലുള്ള
    0.38
    POSITIVE LOGITS
    ിയ
    0.55
    IENTE
    0.47
    İN
    0.47
    d
    0.47
    FIED
    0.46
    LEASE
    0.46
     Improves
    0.46
     único
    0.46
    IMENT
    0.46
     útil
    0.46
    Act Density 0.011%

    No Known Activations