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

    Neuronpedia

    INDEX
    Explanations

    options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Jumlah
    1.32
     企业
    1.25
     Algunos
    1.25
     teclado
    1.23
     Após
    1.23
     ejecutar
    1.21
     Dopo
    1.20
     iniciar
    1.18
    Usuario
    1.17
     初始化
    1.17
    POSITIVE LOGITS
     just
    1.15
     obscure
    1.00
     familiar
    0.95
     in
    0.95
     recesses
    0.89
     not
    0.89
     paired
    0.87
     gastronom
    0.86
     festivals
    0.85
     brochures
    0.84
    Act Density 0.080%

    No Known Activations