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

    Neuronpedia

    INDEX
    Explanations

    terms indicating lack of treatment or undetected conditions

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

    untreated or unread

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ckså
    -0.67
    KommentareTeilen
    -0.56
     للمعارف
    -0.55
    MemoryWarning
    -0.53
     cáps
    -0.52
    يميديا
    -0.52
     Relaciones
    -0.50
     disambiguazione
    -0.50
     Moscú
    -0.49
    ScopeManager
    -0.48
    POSITIVE LOGITS
     unidentified
    0.67
     Un
    0.65
     unstructured
    0.65
     unbalanced
    0.64
    Unnamed
    0.62
     unregistered
    0.61
     unbound
    0.60
    unread
    0.56
     undefined
    0.56
     untreated
    0.55
    Act Density 0.034%

    No Known Activations