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

    Neuronpedia

    INDEX
    Explanations

    language identification or translation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    σε
    0.53
    貝
    0.52
    腳
    0.46
    事業
    0.46
    鶘
    0.46
    嘴
    0.45
     getY
    0.45
    。
    0.44
    村
    0.44
    Ми
    0.44
    POSITIVE LOGITS
     чувство
    0.54
     sowohl
    0.52
     కూడా
    0.48
     também
    0.47
     فنا
    0.46
    itz
    0.46
     manglid
    0.46
     неред
    0.46
    chrane
    0.46
     спокойно
    0.46
    Act Density 0.000%

    No Known Activations