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

    Neuronpedia

    INDEX
    Explanations

    picture, language, concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ambique
    0.38
    usha
    0.38
    eke
    0.38
     seca
    0.37
    imentary
    0.37
    Ago
    0.36
    argue
    0.36
     sèche
    0.36
     घातक
    0.36
    矣
    0.35
    POSITIVE LOGITS
    Picture
    0.41
     Picture
    0.40
     روان
    0.38
    ینو
    0.37
    سلام
    0.37
     rethinking
    0.37
    朖
    0.37
    รูป
    0.36
     cuddling
    0.36
     جنا
    0.36
    Act Density 0.000%

    No Known Activations