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

    Neuronpedia

    INDEX
    Explanations

    unethical and irresponsible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    igsaw
    0.44
    stes
    0.44
     resultContent
    0.42
     кора
    0.41
     landfall
    0.41
     primaryLanguage
    0.41
     permeates
    0.40
     ###
    0.40
     나오는
    0.40
     किफायती
    0.40
    POSITIVE LOGITS
    ﻻ
    0.46
    ادم
    0.42
     Fra
    0.42
     Butter
    0.41
    ad
    0.41
    ઐ
    0.41
     manque
    0.40
     Dus
    0.40
    ਅ
    0.40
     Down
    0.40
    Act Density 9.745%

    No Known Activations