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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     그래서
    0.49
    them
    0.45
    Зна
    0.44
     Зна
    0.43
    그
    0.43
    그래서
    0.43
    相当
    0.42
     İlçesi
    0.42
     Inoltre
    0.42
     Instead
    0.42
    POSITIVE LOGITS
     opposed
    1.38
    ymmet
    1.24
     follows
    1.09
    cribing
    1.08
    sembles
    1.06
     oppose
    1.01
    cribable
    1.01
    sembled
    0.98
     soon
    0.95
    sembling
    0.91
    Act Density 0.198%

    No Known Activations