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

    Neuronpedia

    INDEX
    Explanations

    return status codes not found

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     पाच
    0.40
    憩
    0.40
     sweats
    0.39
    átil
    0.39
     чрезвы
    0.39
     |”
    0.38
     shakes
    0.37
     notícias
    0.37
    (""))
    0.37
     अज्ञात
    0.36
    POSITIVE LOGITS
     Blend
    0.37
     Aut
    0.36
     wont
    0.36
     Karne
    0.36
     Formulas
    0.36
     معد
    0.36
     modalidad
    0.35
     Bi
    0.35
     Payne
    0.35
    چھے
    0.35
    Act Density 0.001%

    No Known Activations