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

    Neuronpedia

    INDEX
    Explanations

    actions related to achievements and milestones

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

    actions and accomplishments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    namespace
    -0.41
     autorytatywna
    -0.38
    ­
    -0.35
    Демографія
    -0.35
     ***!
    -0.34
     rival
    -0.34
    Бележки
    -0.32
    Ծանոթ
    -0.32
    NAMESPACE
    -0.31
     #
    -0.31
    POSITIVE LOGITS
    majánló
    0.79
    RegressionTest
    0.75
    ientras
    0.69
     indígen
    0.69
     ainfi
    0.67
     ſeine
    0.67
     mauva
    0.66
     ddelwed
    0.66
    bootstrapcdn
    0.64
     surla
    0.64
    Act Density 0.061%

    No Known Activations