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

    Neuronpedia

    INDEX
    Explanations

    bending and kneeling actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    க்கள்
    1.44
     большинство
    1.36
     inkább
    1.34
     épaules
    1.33
    𝖙
    1.33
     neka
    1.29
    foto
    1.27
     krwi
    1.26
     ফেলে
    1.26
     pretende
    1.25
    POSITIVE LOGITS
    शील
    1.60
    με
    1.49
    pied
    1.49
    и
    1.47
    p
    1.44
    ませ
    1.42
     있어
    1.38
    ℍ
    1.38
     प्रणाम
    1.37
    ྱི་
    1.37
    Act Density 0.018%

    No Known Activations