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

    Neuronpedia

    INDEX
    Explanations

    loop variable placeholder `%%`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ना
    1.58
    и
    1.58
     وأن
    1.50
    ía
    1.48
    izada
    1.37
    za
    1.33
     أيضاً
    1.32
    ระดับ
    1.30
     և
    1.27
    ड़
    1.27
    POSITIVE LOGITS
    ت
    1.41
    ről
    1.39
     Rupees
    1.36
     skimage
    1.36
    تور
    1.35
     phenols
    1.35
    soever
    1.31
    המ
    1.30
     fooling
    1.30
     kidding
    1.28
    Act Density 0.001%

    No Known Activations