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

    Neuronpedia

    INDEX
    Explanations

    If AI acts unexpectedly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ensibility
    0.42
    ទទួល
    0.41
    hdu
    0.38
     magnitud
    0.38
     VALVE
    0.38
     endoplasmic
    0.38
     algebraica
    0.38
    iodate
    0.38
     photosynthetic
    0.38
    不思議
    0.38
    POSITIVE LOGITS
    แค่
    0.44
     seçenek
    0.43
    涵盖
    0.43
     سایر
    0.42
     بیشتر
    0.42
     lựa
    0.42
     Includes
    0.41
    まずは
    0.41
     chọn
    0.41
     incluyen
    0.41
    Act Density 0.005%

    No Known Activations