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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating processes or actions related to achieving goals or making decisions

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

    demonstrative followed by description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tuturor
    -0.34
     asmen
    -0.34
    AndEndTag
    -0.32
    Obrázky
    -0.31
     Wood
    -0.31
    httphttps
    -0.31
     eletrônico
    -0.30
     deschis
    -0.30
     due
    -0.29
     De
    -0.28
    POSITIVE LOGITS
    parsedMessage
    0.90
    DockStyle
    0.89
     '\\;'
    0.66
    ########.
    0.66
    ectoria
    0.61
    migrationBuilder
    0.60
     للاسماء
    0.60
    enterOuterAlt
    0.58
    rrggbb
    0.57
    astify
    0.57
    Act Density 0.288%

    No Known Activations