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

    Neuronpedia

    INDEX
    Explanations

    official website links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ലെസ്
    0.86
    estrutura
    0.84
    मेद
    0.83
    ADIUM
    0.82
    akkhati
    0.80
     tratado
    0.80
    парат
    0.80
     发表
    0.79
     infraestructura
    0.79
    哳
    0.78
    POSITIVE LOGITS
     Jean
    0.58
     सदर
    0.56
     tím
    0.53
    him
    0.53
     Intu
    0.52
     Acting
    0.52
    go
    0.51
     on
    0.50
    贯彻
    0.50
     jail
    0.50
    Act Density 0.001%

    No Known Activations