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

    Neuronpedia

    INDEX
    Explanations

    units of sound or words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vem
    0.76
     Examin
    0.75
    ශ
    0.74
    টিয়
    0.72
    phere
    0.71
    Organiz
    0.70
     templ
    0.69
     ऐड
    0.68
    编译器
    0.68
    Workshop
    0.68
    POSITIVE LOGITS
    人気の
    0.85
     pollut
    0.73
     인기
    0.72
    क्रामक
    0.71
    iasa
    0.70
     snapped
    0.68
    anki
    0.68
    ित्व
    0.68
    ="_
    0.68
    ड्यू
    0.67
    Act Density 0.000%

    No Known Activations