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

    Neuronpedia

    INDEX
    Explanations

    various languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    وس
    0.48
    ée
    0.47
    що
    0.45
    Backed
    0.44
     позво
    0.44
    ρια
    0.43
    ْر
    0.40
    ρ
    0.40
    ذ
    0.40
    ère
    0.39
    POSITIVE LOGITS
     แบบ
    0.48
     عامر
    0.48
     rechnen
    0.47
     পালন
    0.47
     गलत
    0.46
     freuen
    0.46
     കേരള
    0.46
    imerk
    0.46
     쭉
    0.46
    सीएम
    0.45
    Act Density 0.002%

    No Known Activations