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

    Neuronpedia

    INDEX
    Explanations

    if you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अथवा
    0.45
    allist
    0.43
    atlar
    0.43
    atial
    0.42
    aries
    0.41
    atever
    0.41
     مرات
    0.40
     dajj
    0.40
     posteriori
    0.39
     యుద్ధ
    0.39
    POSITIVE LOGITS
    Bat
    0.46
    DS
    0.42
    Gary
    0.41
     batang
    0.41
     Bat
    0.41
     instead
    0.40
    Assume
    0.40
     rather
    0.40
     swearing
    0.40
    Kyle
    0.39
    Act Density 0.001%

    No Known Activations