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

    Neuronpedia

    INDEX
    Explanations

    objective and progress

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     PlayStation
    0.52
     Ünivers
    0.51
    ܡܪ
    0.51
     السالب
    0.50
     इंस्टॉल
    0.50
    Dining
    0.49
    တယ်။
    0.49
     Antibody
    0.48
     Рі
    0.48
     Großbritannien
    0.48
    POSITIVE LOGITS
     differs
    0.61
     becomes
    0.59
     pascal
    0.56
    ence
    0.55
     vs
    0.55
    arians
    0.55
     nasce
    0.55
    ined
    0.54
     belongs
    0.54
    이란
    0.53
    Act Density 0.000%

    No Known Activations