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

    Neuronpedia

    INDEX
    Explanations

    final answer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝐍
    0.42
     mono
    0.40
    mono
    0.39
    bullet
    0.38
     एडिट
    0.38
    ్యాచ్
    0.38
     szól
    0.35
     known
    0.35
    KNOWN
    0.35
     viral
    0.35
    POSITIVE LOGITS
     verdict
    0.43
     دما
    0.41
    結論
    0.41
     النهائي
    0.41
     مالی
    0.40
     মের
    0.39
    皮膚
    0.39
     décisions
    0.38
    藻
    0.38
     முடி
    0.37
    Act Density 0.002%

    No Known Activations