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

    Neuronpedia

    INDEX
    Explanations

    culture names, future tense, sales tax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     توز
    0.47
    ेला
    0.46
    वतात
    0.44
    क्षात
    0.43
    వులు
    0.43
    𝙪
    0.42
    ുകള്‍
    0.41
    უნ
    0.41
    জ্জিত
    0.41
    дить
    0.40
    POSITIVE LOGITS
     Cahill
    0.48
     سريع
    0.48
    ématique
    0.47
    دد
    0.46
    than
    0.46
    (?:
    0.46
     tans
    0.45
     سر
    0.44
     Philadelphia
    0.44
     biomedical
    0.43
    Act Density 0.000%

    No Known Activations