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

    Neuronpedia

    INDEX
    Explanations

    references to names, titles, and specific variables related to research studies

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

    parts of names and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     preocupes
    -0.59
     tiegħ
    -0.57
    ulongan
    -0.56
     valentín
    -0.55
     čierna
    -0.54
     leão
    -0.54
    colgante
    -0.54
     didalam
    -0.53
     Comprometido
    -0.53
     Infór
    -0.53
    POSITIVE LOGITS
     SwitchCompat
    0.47
    AsUp
    0.46
     CanadaChoose
    0.46
    -(-
    0.46
    esModule
    0.46
    躇
    0.46
    Xna
    0.46
    期刊论文
    0.45
    +#+#
    0.43
    -(
    0.42
    Act Density 0.260%

    No Known Activations