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

    Neuronpedia

    INDEX
    Explanations

    indicators of gratefulness and references to common experiences or expectations

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

    as usual; purpose; again

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.65
     تضيفلها
    -0.55
    RenderAtEndOf
    -0.52
     '\\;'
    -0.46
     propOrder
    -0.45
     continuidad
    -0.44
    ConstraintMaker
    -0.44
    UrlResolution
    -0.44
     typelib
    -0.43
     puentes
    -0.42
    POSITIVE LOGITS
    tar
    0.44
    irat
    0.44
     Tar
    0.44
    Tar
    0.43
    gul
    0.42
     avanti
    0.41
    wach
    0.40
     again
    0.39
     DAC
    0.39
     Gul
    0.39
    Act Density 0.091%

    No Known Activations