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

    Neuronpedia

    INDEX
    Explanations

    Core g coc

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Incorrect
    0.82
    殃
    0.73
     violate
    0.72
    ASTIC
    0.72
    """
    0.71
    Incorrect
    0.71
    Not
    0.70
    وقال
    0.70
    untary
    0.70
    ↵
    0.69
    POSITIVE LOGITS
     conductores
    0.82
     gestão
    0.80
     управління
    0.78
    องค์
    0.77
    it
    0.76
    ли
    0.74
    시
    0.74
    ีก
    0.73
     проведення
    0.72
     ನಗರ
    0.72
    Act Density 0.002%

    No Known Activations