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

    Neuronpedia

    INDEX
    Explanations

    harm and vulnerability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Пі
    0.47
     ক্রিকে
    0.46
    ل
    0.46
    ق
    0.46
     پوکر
    0.46
    と思いますが
    0.44
    সম্মত
    0.43
    }",
    0.43
    IsNullOrEmpty
    0.43
    緬
    0.43
    POSITIVE LOGITS
    achtung
    0.47
    downloads
    0.44
     constitutive
    0.43
     founding
    0.43
    /
    0.43
    gran
    0.42
    ate
    0.42
    AX
    0.42
    et
    0.41
    মণ্ড
    0.41
    Act Density 0.004%

    No Known Activations