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

    Neuronpedia

    INDEX
    Explanations

    disclaimers about professional advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ગ
    0.49
     ою
    0.44
    婄
    0.42
    ਗੇ
    0.41
    福岡
    0.41
     объек
    0.41
    ाब
    0.41
     бою
    0.41
    ਗ
    0.40
     तुर
    0.40
    POSITIVE LOGITS
     Trav
    0.47
     flat
    0.45
    有两种
    0.44
     trusty
    0.43
    庐
    0.42
     financial
    0.42
    жная
    0.42
     Ά
    0.41
    vers
    0.41
     Flat
    0.41
    Act Density 0.000%

    No Known Activations