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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    یی
    0.49
     وبعد
    0.47
    ngthen
    0.47
     Children
    0.46
    常见的
    0.43
    阁
    0.43
     Secondary
    0.42
    uldron
    0.42
     مشابه
    0.42
     रक
    0.42
    POSITIVE LOGITS
     вулка
    0.52
    蚜
    0.47
    アイス
    0.46
    чества
    0.45
     piante
    0.45
    פל
    0.45
    ף
    0.45
     grasses
    0.45
     રી
    0.44
    ন্তা
    0.44
    Act Density 0.002%

    No Known Activations