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

    Neuronpedia

    INDEX
    Explanations

    abbreviations and acronyms commonly used in scientific and technical contexts

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

    initialisms ending in Z, Y, or W

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ioutil
    -0.49
     utafitiHapana
    -0.46
    ſelf
    -0.44
    +#+#
    -0.44
    sizeCache
    -0.43
    ɵɵelementEnd
    -0.43
    pośred
    -0.43
    ifflin
    -0.43
     مشين
    -0.41
    ModelAdmin
    -0.41
    POSITIVE LOGITS
    SW
    0.49
    bkz
    0.46
     SW
    0.46
    transQ
    0.45
    cw
    0.44
    oy
    0.43
    sinx
    0.43
    izy
    0.41
    sety
    0.41
    tw
    0.41
    Act Density 0.238%

    No Known Activations