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

    Neuronpedia

    INDEX
    Explanations

    utf- encoding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﯽ
    0.41
     সফদর
    0.39
    HandleTypeDef
    0.39
     ";
    0.38
    IFO
    0.38
    袒
    0.38
    Gul
    0.38
    轰
    0.37
    IFUL
    0.37
    ﻱ
    0.37
    POSITIVE LOGITS
    olska
    0.40
    ences
    0.38
    ensch
    0.38
    elf
    0.38
    widgets
    0.35
    oss
    0.34
     gong
    0.34
    ure
    0.33
     listop
    0.33
    eli
    0.33
    Act Density 0.001%

    No Known Activations