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

    Neuronpedia

    INDEX
    Explanations

    sequences of special punctuation marks or possibly certain identifiers within a text

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

    names with initials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.61
     Normdatei
    -0.54
    troppo
    -0.46
    лтамалар
    -0.45
     Paesi
    -0.44
     giud
    -0.44
     recente
    -0.42
    ftagPool
    -0.42
    bringer
    -0.42
    InitVars
    -0.42
    POSITIVE LOGITS
    PostInfinity
    0.37
    참고
    0.36
     оригіналу
    0.35
    IFORNIA
    0.35
    WSGI
    0.34
    ovsky
    0.33
    ValueStyle
    0.33
    setContentView
    0.32
     lagi
    0.31
    Fiche
    0.31
    Act Density 0.101%

    No Known Activations