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

    Neuronpedia

    INDEX
    Explanations

    code constructors and declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    วก
    0.41
    stown
    0.38
     thy
    0.38
    स्टन
    0.37
     Tok
    0.37
    ির
    0.36
    __,
    0.36
    ="...">
    0.36
    পত্রের
    0.36
     Subdistrict
    0.36
    POSITIVE LOGITS
     {}
    0.52
     ‬
    0.44
    rası
    0.41
    {}
    0.39
    CIS
    0.37
     }}
    0.37
    的值
    0.37
     ⠀
    0.37
    ș
    0.37
     الأد
    0.36
    Act Density 0.000%

    No Known Activations