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

    Neuronpedia

    INDEX
    Explanations

    Component-Based architecture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IN
    0.98
    EST
    0.76
    ف
    0.75
    ك
    0.75
    ך
    0.74
    لی
    0.73
    OLYBD
    0.73
    ัพท์
    0.73
    OUT
    0.73
    CHE
    0.73
    POSITIVE LOGITS
    t
    1.09
    d
    0.86
     components
    0.80
    ur
    0.80
    ről
    0.80
    tul
    0.77
    tete
    0.75
     composants
    0.74
    taining
    0.72
    rna
    0.72
    Act Density 0.017%

    No Known Activations