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

    Neuronpedia

    INDEX
    Explanations

    choices or alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     بسیاری
    0.48
     بسیار
    0.48
     весьма
    0.48
     तमाम
    0.45
     számos
    0.45
     모든
    0.44
     tudo
    0.44
     अनेक
    0.43
     довольно
    0.43
    ها
    0.42
    POSITIVE LOGITS
     either
    0.73
    하거나
    0.63
     અથવા
    0.60
     hoặc
    0.56
     themselves
    0.54
     veya
    0.54
     algún
    0.54
    或
    0.53
     or
    0.52
    either
    0.52
    Act Density 0.037%

    No Known Activations