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

    Neuronpedia

    INDEX
    Explanations

    normalize the `!` operator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     बचना
    0.44
     parmesan
    0.43
     настоя
    0.42
     intestines
    0.41
     birch
    0.41
     skulls
    0.41
     በኋላ
    0.41
     spice
    0.40
     AO
    0.40
     skull
    0.39
    POSITIVE LOGITS
    قی
    0.53
    effort
    0.53
    في
    0.51
    a
    0.51
    تی
    0.50
    시
    0.49
    بی
    0.48
    .
    0.48
    Sur
    0.47
     autora
    0.47
    Act Density 0.001%

    No Known Activations