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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating inadequacies or deficiencies in capabilities and resources

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

    lack of ability or capacity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Winaray
    -0.40
    /***/
    -0.38
    .*")]
    -0.35
    TemporalType
    -0.35
     مشين
    -0.34
    tahui
    -0.34
    Accessed
    -0.33
    RLock
    -0.33
     Sexton
    -0.32
    tvguidetime
    -0.32
    POSITIVE LOGITS
    TagMode
    0.66
     unprepared
    0.60
     incapable
    0.59
     kapac
    0.56
    MLLoader
    0.56
     powerless
    0.52
     incapa
    0.50
     vermogen
    0.48
     overwhelmed
    0.47
    DrawerToggle
    0.47
    Act Density 0.040%

    No Known Activations