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

    Neuronpedia

    INDEX
    Explanations

    highly regarded

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    daar
    1.37
    अमेरिकी
    1.30
    ك
    1.30
    nikov
    1.28
    ﺏ
    1.27
    byshev
    1.24
    estrian
    1.23
     تغییر
    1.22
    Today
    1.21
    rimiento
    1.19
    POSITIVE LOGITS
     Selamat
    0.98
    pyrim
    0.96
    ซ์
    0.91
    (:,:,
    0.90
    arbeiten
    0.89
    celles
    0.89
     regard
    0.89
    ventyConfig
    0.88
    rets
    0.88
    ⑬
    0.87
    Act Density 0.000%

    No Known Activations