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

    Neuronpedia

    INDEX
    Explanations

    together with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     বিষয়
    0.52
     বিষয়
    0.50
    ）（
    0.50
     목적
    0.49
    hFile
    0.49
     사항
    0.47
    hna
    0.46
     ایسی
    0.45
     ಉದ್ದ
    0.45
     지정
    0.45
    POSITIVE LOGITS
    с
    0.74
    กับ
    0.66
     με
    0.65
    ü
    0.60
    า
    0.59
    т
    0.56
     với
    0.55
    á
    0.54
    ia
    0.53
     dengan
    0.52
    Act Density 0.001%

    No Known Activations