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

    Neuronpedia

    INDEX
    Explanations

    code and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ;
    0.52
    s
    0.49
    बै
    0.49
    Animation
    0.49
    FormatException
    0.45
    앉
    0.44
    owl
    0.44
    kPa
    0.44
    fireFlower
    0.44
    الأ
    0.44
    POSITIVE LOGITS
     поможет
    0.52
    φέρει
    0.45
     помогает
    0.44
     κάνει
    0.43
     सर्जरी
    0.41
     développe
    0.41
     revi
    0.39
    自己在
    0.39
     conn
    0.38
     prévenir
    0.38
    Act Density 0.001%

    No Known Activations