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

    Neuronpedia

    INDEX
    Explanations

    elements related to performance improvement and enhancements in systems or processes

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

    improving or increasing performance metrics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rigated
    -0.39
    upol
    -0.38
    quele
    -0.38
    appartamento
    -0.38
    FS
    -0.37
    转身
    -0.37
    fs
    -0.36
    hores
    -0.36
    つか
    -0.36
    alnya
    -0.35
    POSITIVE LOGITS
    хьтан
    0.50
    stylers
    0.49
    WebElementEntity
    0.49
    انتهای
    0.49
    Vidite
    0.48
     Améli
    0.47
    aarrggbb
    0.46
    +#+#
    0.45
    awtextra
    0.44
    évaluateur
    0.43
    Act Density 0.066%

    No Known Activations