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

    Neuronpedia

    INDEX
    Explanations

    HTML tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Beruf
    -0.77
     Swiss
    -0.75
     Dafür
    -0.73
     Василь
    -0.72
    Appear
    -0.71
    aspectj
    -0.71
    воз
    -0.69
    bowler
    -0.68
    czę
    -0.68
    SaveChangesAsync
    -0.67
    POSITIVE LOGITS
     addon
    0.85
    ficado
    0.81
     direita
    0.77
    KAS
    0.77
     Stande
    0.76
    ιά
    0.75
    Gala
    0.74
    汰
    0.73
     tiện
    0.73
    Addon
    0.73
    Act Density 0.002%

    No Known Activations