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

    Neuronpedia

    INDEX
    Explanations

    hands and knees

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    터를
    0.50
     gerar
    0.49
    전을
    0.49
    터
    0.49
     societal
    0.48
     drawback
    0.47
    زن
    0.47
     accéder
    0.46
    飾
    0.46
     undis
    0.46
    POSITIVE LOGITS
     रेपो
    0.59
    lice
    0.56
     Potatoes
    0.55
     Spelling
    0.55
     Palms
    0.54
     Pasand
    0.54
     Если
    0.53
     Пусть
    0.52
     Poisson
    0.52
     Prayers
    0.52
    Act Density 0.000%

    No Known Activations