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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    h
    0.44
    a
    0.41
    Shivam
    0.37
    າ
    0.36
    ᱞ
    0.35
    ர்
    0.34
    ai
    0.34
    ီ
    0.33
    Cell
    0.32
     தொடர்பான
    0.32
    POSITIVE LOGITS
     with
    0.44
    تي
    0.39
     of
    0.39
    تب
    0.36
    ات
    0.35
    يت
    0.35
    ten
    0.33
    ון
    0.33
     (
    0.33
    л
    0.33
    Act Density 0.000%

    No Known Activations