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

    Neuronpedia

    INDEX
    Explanations

    code fragments and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    7
    0.59
    ７
    0.54
    .
    0.52
     މ
    0.52
    ېر
    0.52
    ，
    0.51
    6
    0.51
    肴
    0.49
    ﻔ
    0.48
    addKill
    0.48
    POSITIVE LOGITS
     be
    0.56
    re
    0.56
    ha
    0.49
    ki
    0.49
     palabras
    0.47
     неболь
    0.47
     школы
    0.46
     schwar
    0.45
     CuSO
    0.44
     публикации
    0.44
    Act Density 0.465%

    No Known Activations