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

    Neuronpedia

    INDEX
    Explanations

    reach out for help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ";"
    0.26
     crepe
    0.26
     upwards
    0.25
     linéaire
    0.25
     linguaggio
    0.25
    x
    0.25
     المشروع
    0.25
     매우
    0.25
    xb
    0.25
     similaire
    0.25
    POSITIVE LOGITS
    ’
    0.30
    需
    0.29
    ਾ
    0.28
    де
    0.28
    '
    0.28
    各種
    0.28
    कर
    0.27
    يا
    0.26
    ه
    0.26
    ان
    0.26
    Act Density 0.026%

    No Known Activations