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

    Neuronpedia

    INDEX
    Explanations

    explanation of concepts and their relation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    時計
    0.41
     quantifier
    0.40
    сет
    0.39
    θεί
    0.38
    !}{
    0.37
    ਅ
    0.37
     linguistic
    0.36
    clinton
    0.36
     clopen
    0.36
    ту
    0.35
    POSITIVE LOGITS
    解説
    0.40
    aboration
    0.39
     Capitalism
    0.39
     soporte
    0.38
    olecules
    0.37
    ZS
    0.37
    resos
    0.37
    ראל
    0.37
     Nationalism
    0.37
     परमा
    0.37
    Act Density 0.001%

    No Known Activations