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

    Neuronpedia

    INDEX
    Explanations

    phrases or structures related to instructions or guidelines

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

    let or tips

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AttributeSet
    -0.61
    __':
    -0.51
    >",
    -0.50
    +#+
    -0.49
    ########.
    -0.47
     disambiguazione
    -0.47
    SPATH
    -0.45
    annique
    -0.45
    !*\
    -0.44
    ագրություններ
    -0.44
    POSITIVE LOGITS
    хьтан
    0.47
    oredCriteria
    0.47
    Diweddarwch
    0.44
    ConstraintMaker
    0.41
    ngdoc
    0.39
    expandindo
    0.38
    ۣ
    0.37
    readFileSync
    0.36
    Istorija
    0.35
     itinéraires
    0.34
    Act Density 0.088%

    No Known Activations