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

    Neuronpedia

    INDEX
    Explanations

    access open Gemini zip

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    дох
    0.39
    òu
    0.39
     floor
    0.34
    แนว
    0.34
     Нов
    0.34
    斛
    0.34
    І
    0.34
    ึ้น
    0.33
     kept
    0.33
    ленні
    0.33
    POSITIVE LOGITS
    酛
    0.41
     учитель
    0.38
     पाती
    0.38
     المعل
    0.38
     মুক্তিফৌজ
    0.38
     الصح
    0.36
     instructional
    0.36
    }-(
    0.36
    ကြည့်
    0.36
     instruction
    0.36
    Act Density 0.002%

    No Known Activations