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

    Neuronpedia

    INDEX
    Explanations

    equation, transform, proper nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    u
    1.63
    IZED
    1.30
    ים
    1.17
    isasi
    1.17
    s
    1.09
    ಲ್ಲಿ
    1.09
    i
    1.09
    speople
    1.08
    sms
    1.07
    uZ
    1.07
    POSITIVE LOGITS
    ри
    1.09
     combing
    1.09
    ⺌
    1.05
     polyd
    1.02
     handels
    1.02
     aerosols
    0.98
     continually
    0.95
     streaks
    0.95
     spurious
    0.95
     assembling
    0.94
    Act Density 0.008%

    No Known Activations