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

    Neuronpedia

    INDEX
    Explanations

    step-by-step instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hedon
    0.53
     bah
    0.47
     serviços
    0.47
     pwm
    0.46
     servizio
    0.46
     servicios
    0.45
     sozial
    0.44
     spree
    0.43
     gior
    0.41
     parab
    0.41
    POSITIVE LOGITS
     कठिन
    0.47
    тельно
    0.45
    remainder
    0.44
    Multiply
    0.44
    Think
    0.43
    Prepare
    0.41
     Carefully
    0.41
    Incorpor
    0.41
     иллюстрация
    0.41
    apply
    0.41
    Act Density 0.001%

    No Known Activations