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

    Neuronpedia

    INDEX
    Explanations

    card games and drinks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eso
    0.52
     continuamos
    0.50
     Kham
    0.49
    abandon
    0.49
     fundamental
    0.48
    prior
    0.48
    *',
    0.48
    ');
    0.47
     vamos
    0.47
     adi
    0.47
    POSITIVE LOGITS
    ورت
    0.53
    ्रीट
    0.52
    تری
    0.49
    ﺳ
    0.45
     س
    0.44
    لان
    0.43
     සඳ
    0.42
    ôtel
    0.41
     марке
    0.41
    ोल
    0.41
    Act Density 0.000%

    No Known Activations