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

    Neuronpedia

    INDEX
    Explanations

    actions and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     кере
    0.50
     ánh
    0.45
    am
    0.44
     زين
    0.44
    bedkar
    0.43
     cheery
    0.42
    徳
    0.42
     বোঝার
    0.42
    目は
    0.41
    jahteraan
    0.40
    POSITIVE LOGITS
     internal
    0.43
     시스템
    0.42
    ﺤ
    0.42
    न्होंने
    0.41
     COLLECT
    0.40
    너지
    0.39
    ilat
    0.39
     which
    0.39
    atinum
    0.38
     Oiseaux
    0.38
    Act Density 0.001%

    No Known Activations