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

    Neuronpedia

    INDEX
    Explanations

    body parts trembling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    म्र
    2.27
    ો
    2.22
    म
    2.15
    ান
    2.10
    र
    2.09
    en
    2.05
    स्थ्य
    2.03
    ä
    2.02
    yen
    2.02
    ı
    2.02
    POSITIVE LOGITS
    ت
    2.45
    EF
    2.29
    تام
    2.22
    са
    1.93
    𝗋
    1.88
     Qxb
    1.85
    ीट
    1.84
    eliers
    1.82
    г
    1.82
    нт
    1.81
    Act Density 0.021%

    No Known Activations