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

    Neuronpedia

    INDEX
    Explanations

    args: The

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ब्याज
    0.37
     учетом
    0.32
     бизнеса
    0.31
    私も
    0.31
     ఉత్ప
    0.31
    řejmě
    0.31
    这些人
    0.31
     paralysie
    0.30
     борь
    0.30
    wives
    0.29
    POSITIVE LOGITS
     the
    0.63
     The
    0.54
    the
    0.52
    The
    0.49
     an
    0.45
     string
    0.42
     determines
    0.40
     required
    0.39
     THE
    0.39
     a
    0.38
    Act Density 0.593%

    No Known Activations