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

    Neuronpedia

    INDEX
    Explanations

    beans, bilaterally, credibly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⅼ
    0.91
    ลาคม
    0.87
     NOR
    0.83
     каттоо
    0.83
    haltung
    0.82
     정사각형
    0.80
    အစိတ်အပိုင်း
    0.79
    ibban
    0.79
    0.79
    視覺
    0.78
    POSITIVE LOGITS
    n
    1.38
    на
    0.92
    se
    0.84
    ad
    0.84
    ung
    0.84
    so
    0.83
    r
    0.83
    す
    0.81
    te
    0.80
    ap
    0.80
    Act Density 0.000%

    No Known Activations