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

    Neuronpedia

    INDEX
    Explanations

    configuration structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ونز
    0.39
    )+"
    0.37
    تقدم
    0.37
    साम
    0.36
    зка
    0.35
    )+'
    0.34
    :@"
    0.34
    getragen
    0.33
     Beasley
    0.33
    ينات
    0.33
    POSITIVE LOGITS
     [],
    0.61
     {
    0.55
     {},
    0.50
    true
    0.46
    {}
    0.45
    [],
    0.44
    {},
    0.43
    {
    0.42
     true
    0.41
     [
    0.40
    Act Density 0.015%

    No Known Activations