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

    Neuronpedia

    INDEX
    Explanations

    If... then conditional

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Education
    0.54
    níku
    0.50
    education
    0.50
    🫰
    0.49
     मुख्य
    0.48
     Pendidikan
    0.48
     Gebrauch
    0.48
     Sora
    0.47
     स्वचालित
    0.47
    ෂ්
    0.46
    POSITIVE LOGITS
     bonnes
    0.47
    LEE
    0.46
     errors
    0.43
     excess
    0.42
     reigned
    0.42
    Aprend
    0.42
    Quando
    0.42
     as
    0.41
    르고
    0.41
     a
    0.41
    Act Density 0.003%

    No Known Activations