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

    Neuronpedia

    INDEX
    Explanations

    general length

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     obiettivo
    1.06
     internationaux
    1.04
     ampio
    0.94
     всі
    0.93
     anglais
    0.93
     argumento
    0.93
     atriz
    0.93
     artisti
    0.93
     interno
    0.92
     utenti
    0.92
    POSITIVE LOGITS
    н
    0.93
    ett
    0.88
    ut
    0.82
    น
    0.77
    नं
    0.76
    incre
    0.74
    示す
    0.74
    ag
    0.73
     on
    0.73
    น้อย
    0.70
    Act Density 1.903%

    No Known Activations