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

    Neuronpedia

    INDEX
    Explanations

    names and languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     leichter
    0.45
     tov
    0.42
     candidature
    0.42
     voh
    0.41
     hight
    0.40
     هار
    0.39
     حدا
    0.39
     فلم
    0.38
     nevy
    0.38
     இருக்கிறார்
    0.38
    POSITIVE LOGITS
    წიფ
    0.44
     cuyos
    0.42
    ที่คุณ
    0.40
     שלך
    0.39
     která
    0.39
     Blak
    0.39
     συμφ
    0.39
    我认为
    0.38
     whose
    0.38
    ogne
    0.36
    Act Density 0.017%

    No Known Activations