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

    Neuronpedia

    INDEX
    Explanations

    blue creatures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     અને
    0.54
    Hepinize
    0.53
    肿瘤
    0.53
     любовь
    0.50
     می‌کند
    0.47
     হলেন
    0.47
    Spiel
    0.46
    的生活
    0.45
    LetterIndex
    0.45
     personaggio
    0.45
    POSITIVE LOGITS
    ק
    0.46
    t
    0.46
    td
    0.45
    f
    0.44
    ంగు
    0.43
    d
    0.43
    ق
    0.43
     hydroly
    0.43
    msub
    0.42
     improvements
    0.41
    Act Density 0.011%

    No Known Activations