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

    Neuronpedia

    INDEX
    Explanations

    integer literals and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ꮟ
    0.60
    oya
    0.58
     ColumnName
    0.56
     ғ
    0.56
     "("
    0.55
    ഡിയ
    0.54
    ízo
    0.54
    Ꮢ
    0.54
    ormais
    0.54
    फो
    0.54
    POSITIVE LOGITS
     int
    0.92
    Int
    0.90
    int
    0.90
    INT
    0.83
    8
    0.81
     Int
    0.78
     INT
    0.77
     orange
    0.75
     réserver
    0.75
    Orange
    0.75
    Act Density 0.410%

    No Known Activations