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

    Neuronpedia

    INDEX
    Explanations

    Writes the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    0.68
    י
    0.59
    ી
    0.58
    يته
    0.55
     Mahabhar
    0.54
    יים
    0.52
    Framebuffer
    0.51
     nó
    0.50
    給我
    0.49
    i
    0.49
    POSITIVE LOGITS
    ättning
    0.50
     expediency
    0.46
     retirement
    0.45
     ताकि
    0.44
    ობით
    0.44
     मृत्यु
    0.44
    रात
    0.43
    हित्य
    0.43
     tabulation
    0.42
     activities
    0.42
    Act Density 0.000%

    No Known Activations