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

    Neuronpedia

    INDEX
    Explanations

    torqueCurve

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    本
    0.49
    ه
    0.44
    ין
    0.44
    scientific
    0.43
    د
    0.43
    domestic
    0.43
    י
    0.43
    ሖ
    0.42
    Approximately
    0.42
    ד
    0.42
    POSITIVE LOGITS
     ð
    0.52
     مرا
    0.49
    所謂
    0.49
     Requested
    0.45
     ประเภท
    0.44
     Agreements
    0.44
    mrow
    0.44
     Bạn
    0.44
     Chois
    0.44
     ระบบ
    0.44
    Act Density 0.002%

    No Known Activations