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

    Neuronpedia

    INDEX
    Explanations

    types of information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    不停
    0.57
     افزایش
    0.53
    癃
    0.52
    大量的
    0.51
    ⵅ
    0.50
     liberación
    0.50
    大量
    0.49
    စေ
    0.48
    ⵚ
    0.48
    طنين
    0.47
    POSITIVE LOGITS
     type
    1.09
     name
    0.95
    type
    0.84
     тип
    0.82
     типу
    0.81
     types
    0.81
     applicable
    0.78
     names
    0.78
     preference
    0.77
     jenis
    0.76
    Act Density 1.357%

    No Known Activations