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

    Neuronpedia

    INDEX
    Explanations

    structured list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    if
    0.46
     if
    0.43
     ولم
    0.42
     هذه
    0.40
     नहीं
    0.39
     الاتحاد
    0.39
     այդ
    0.39
     بعد
    0.38
    of
    0.38
     fellow
    0.38
    POSITIVE LOGITS
    А
    0.43
    رسٹ
    0.43
     workpiece
    0.39
     tractable
    0.38
     eukaryotes
    0.38
    ため
    0.37
    фикси
    0.37
    vori
    0.36
    dır
    0.36
     konkret
    0.36
    Act Density 2.478%

    No Known Activations