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

    Neuronpedia

    INDEX
    Explanations

    html closing tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0x80>
    0.40
    водится
    0.36
     (
    0.35
     ως
    0.34
     μό
    0.34
     )\
    0.34
     ي
    0.33
     navigateur
    0.33
    ică
    0.33
    сно
    0.32
    POSITIVE LOGITS
    in
    0.70
    a
    0.68
    i
    0.61
    f
    0.56
    ing
    0.56
    le
    0.55
    ه
    0.54
    ה
    0.49
    er
    0.47
    economic
    0.46
    Act Density 0.310%

    No Known Activations