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

    Neuronpedia

    INDEX
    Explanations

    code structure and options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     μέσα
    0.36
     ভ
    0.35
     ionic
    0.34
     handyman
    0.33
     planting
    0.33
     and
    0.33
     plush
    0.33
     这个
    0.33
     locking
    0.33
     warms
    0.33
    POSITIVE LOGITS
     conclusiones
    0.39
    最終
    0.38
    dasarkan
    0.37
    RESULTS
    0.36
     demoral
    0.36
    Выберите
    0.36
     rendement
    0.36
     انصاف
    0.36
    ЕН
    0.35
     Entscheidung
    0.35
    Act Density 0.050%

    No Known Activations