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

    Neuronpedia

    INDEX
    Explanations

    bolded text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ž
    0.43
     covariate
    0.42
     🥰
    0.42
     stipulation
    0.41
     🙂
    0.40
    😚
    0.40
     gzip
    0.40
    ☺️
    0.40
    任意の
    0.40
     badass
    0.39
    POSITIVE LOGITS
    CONTENTS
    0.61
    indd
    0.57
    www
    0.56
     www
    0.55
    SPECIAL
    0.55
    PHOTO
    0.54
    TECHN
    0.54
    EVENTS
    0.53
     SPECIAL
    0.53
     WHAT
    0.53
    Act Density 0.001%

    No Known Activations