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

    Neuronpedia

    INDEX
    Explanations

    Arabic text

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    umsal
    0.41
    ùm
    0.40
    ạng
    0.38
    raintree
    0.37
    ysets
    0.37
     passato
    0.36
    養
    0.36
    nen
    0.36
     pern
    0.36
     Umfang
    0.36
    POSITIVE LOGITS
     Бала
    0.44
     highlighted
    0.43
     الج
    0.38
     balas
    0.38
     بالأ
    0.38
     highlighting
    0.35
     بالح
    0.35
     اعلام
    0.34
     कट
    0.34
    empo
    0.34
    Act Density 0.000%

    No Known Activations