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

    Neuronpedia

    INDEX
    Explanations

    to achieve a goal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ف
    1.42
    it
    1.38
    p
    1.37
    ت
    1.35
    د
    1.25
    1
    1.20
    ly
    1.20
    м
    1.17
    я
    1.17
    س
    1.17
    POSITIVE LOGITS
    🛖
    1.25
    ljenje
    1.10
    써
    1.09
     ﺍﻟ
    1.08
    睄
    1.08
    État
    1.07
    妽
    1.06
    UGH
    1.05
    స్టు
    1.04
    的内容
    1.03
    Act Density 1.370%

    No Known Activations