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

    Neuronpedia

    INDEX
    Explanations

    foreign languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Regards
    0.39
    ホール
    0.38
     ColumnName
    0.37
     Basketball
    0.36
     resistors
    0.36
    ⛹
    0.36
    固有
    0.35
    ہور
    0.35
    —-
    0.35
    degenerate
    0.35
    POSITIVE LOGITS
     expanding
    0.46
     totale
    0.43
     erweit
    0.40
    λυ
    0.39
     viktigt
    0.39
     beschik
    0.39
     full
    0.39
     dõi
    0.38
     दोस्त
    0.38
     solv
    0.38
    Act Density 0.000%

    No Known Activations