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

    Neuronpedia

    INDEX
    Explanations

    phrases that express personal reflections, opinions, or predictions

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

    expressing belief or desire

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     conducción
    -0.47
    httphttps
    -0.45
     gravedad
    -0.43
     defaultstate
    -0.42
    KURZBESCHREIBUNG
    -0.41
    MACHINE
    -0.41
     combinación
    -0.39
    存于互联网档案馆
    -0.39
     MACHINE
    -0.38
    uxxxx
    -0.38
    POSITIVE LOGITS
    oredCriteria
    0.57
    يكب
    0.55
    MigrationBuilder
    0.48
     NSCoder
    0.48
    GTCX
    0.47
     ComVisible
    0.46
     getEmail
    0.46
    Dil
    0.45
    sizeCache
    0.45
     Meksiku
    0.44
    Act Density 0.096%

    No Known Activations