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

    Neuronpedia

    INDEX
    Explanations

    references to specific variables, functions, or symbols in mathematical or scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    med/reg, military fit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.47
     esternos
    -0.46
     дописавши
    -0.45
    Marshaller
    -0.44
    PullParser
    -0.43
     MainAxisSize
    -0.43
    :✨
    -0.42
    #+#
    -0.42
    Personensuche
    -0.42
    forChild
    -0.41
    POSITIVE LOGITS
     puol
    0.39
     herói
    0.37
    tdb
    0.36
    roach
    0.36
    °.
    0.35
     intptr
    0.35
     deaf
    0.35
     verhalen
    0.34
     bereiken
    0.34
    ?!”
    0.34
    Act Density 0.174%

    No Known Activations