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

    Neuronpedia

    INDEX
    Explanations

    creating a character

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    тивных
    0.45
    尋
    0.43
    oid
    0.42
    ダン
    0.42
    Exporter
    0.41
    ［
    0.41
     перемо
    0.40
    Vita
    0.40
    昅
    0.40
    Won
    0.39
    POSITIVE LOGITS
    aney
    0.45
     eligibility
    0.45
     only
    0.44
     ifelse
    0.44
    க்கப்பட்டுள்ளது
    0.44
     sono
    0.42
     Обще
    0.42
    pleClass
    0.42
     els
    0.42
     Committees
    0.41
    Act Density 0.010%

    No Known Activations