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

    Neuronpedia

    INDEX
    Explanations

    references to international collaboration and diplomacy

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

    denounced, safety, summoned, speech, contention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    KURZBESCHREIBUNG
    -0.49
    Britannique
    -0.48
     незавершена
    -0.48
    TQ
    -0.47
    IsContent
    -0.46
    fuge
    -0.46
    RTDA
    -0.45
     تعدى
    -0.45
     []:
    -0.44
    Populations
    -0.44
    POSITIVE LOGITS
     indisponible
    0.41
    Embeddable
    0.36
     hemel
    0.36
    úgó
    0.35
    ﷺ
    0.35
     nifer
    0.34
    rizona
    0.33
    RectangleBorder
    0.33
     Infór
    0.33
    olalar
    0.32
    Act Density 0.006%

    No Known Activations