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

    Neuronpedia

    INDEX
    Explanations

    reporting, Timestamp, limit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    idimensional
    0.46
     riguard
    0.44
    ӥ
    0.43
    lamualaikum
    0.40
    érg
    0.40
    摈
    0.40
    myTransform
    0.40
     macroph
    0.39
    ╝
    0.39
     glLightfv
    0.39
    POSITIVE LOGITS
    アン
    0.42
     فل
    0.41
     Paras
    0.39
    เจ
    0.37
     P
    0.37
    쿤
    0.37
    اط
    0.36
    那個
    0.36
     filer
    0.36
    Paras
    0.36
    Act Density 0.000%

    No Known Activations