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

    Neuronpedia

    INDEX
    Explanations

    execute commands or find information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     পঞ্চম
    0.46
     съем
    0.46
    皆
    0.46
     pią
    0.46
     pięk
    0.46
    uí
    0.45
    ツアー
    0.45
    imą
    0.45
    ickým
    0.45
     времени
    0.45
    POSITIVE LOGITS
     :,
    0.47
     on
    0.46
     DIY
    0.45
     Safe
    0.44
     P
    0.43
     Sosial
    0.43
     Fine
    0.42
     safe
    0.41
    ؤلاء
    0.41
     Biod
    0.41
    Act Density 0.001%

    No Known Activations