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

    Neuronpedia

    INDEX
    Explanations

    need for wonder

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    shaw
    0.43
    ዃ
    0.39
    িত্র
    0.39
    ষিত
    0.38
     المسي
    0.38
    writeFileSync
    0.38
     అయినా
    0.37
    ötet
    0.37
     আপনা
    0.37
    equalsIgnoreCase
    0.36
    POSITIVE LOGITS
     man
    0.41
     "~
    0.39
     Confidence
    0.37
     pause
    0.37
     ABA
    0.37
     Background
    0.36
     thư
    0.36
     Pause
    0.36
    쉽
    0.36
     btn
    0.36
    Act Density 0.000%

    No Known Activations