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

    Neuronpedia

    INDEX
    Explanations

    don't know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ن
    2.17
    ت
    1.67
    ف
    1.64
     galima
    1.61
    лите
    1.58
     וי
    1.57
    আ
    1.55
    зать
    1.53
    ה
    1.51
    ز
    1.50
    POSITIVE LOGITS
     autres
    1.52
    crates
    1.48
    ou
    1.48
    digits
    1.47
    ab
    1.42
    DEFINITION
    1.42
    definitions
    1.40
    ى
    1.40
    ud
    1.39
    deeds
    1.39
    Act Density 0.110%

    No Known Activations