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

    Neuronpedia

    INDEX
    Explanations

    numbers and ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ка
    0.73
    юк
    0.62
    udy
    0.59
    на
    0.58
    ня
    0.58
     innych
    0.57
    ку
    0.57
    рга
    0.57
     Eintrag
    0.56
     We
    0.55
    POSITIVE LOGITS
    長さ
    0.67
     detoxification
    0.61
     लगभग
    0.60
    ًا
    0.58
     chihuahua
    0.57
     ત્રણ
    0.57
     quadruple
    0.55
    ían
    0.54
     revolver
    0.54
     superpower
    0.54
    Act Density 0.337%

    No Known Activations