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

    Neuronpedia

    INDEX
    Explanations

    cause damage or indicate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    按照
    0.49
    党委
    0.48
     استخدم
    0.44
    มี
    0.43
    bilder
    0.43
     opinions
    0.43
     versions
    0.41
     embody
    0.41
     استخدام
    0.41
    侎
    0.41
    POSITIVE LOGITS
     bå
    0.44
     pieza
    0.44
     곡
    0.43
    ৮
    0.42
    ędzynarod
    0.42
     rumah
    0.42
     پھی
    0.41
    pof
    0.41
    爽
    0.41
    ∘
    0.41
    Act Density 0.007%

    No Known Activations