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

    Neuronpedia

    INDEX
    Explanations

    the presence and frequency of specific common words related to names or titles

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

    National airs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    İstinadlar
    -0.53
     plátano
    -0.51
     olympique
    -0.50
     aprobado
    -0.47
     silicona
    -0.47
     personalizado
    -0.46
     prohibido
    -0.45
     almendras
    -0.45
     olímp
    -0.44
    arakhand
    -0.44
    POSITIVE LOGITS
     intStringLen
    0.50
    SharedCtor
    0.49
     initState
    0.46
    parsedMessage
    0.45
     getConnection
    0.42
     Cars
    0.42
    FLD
    0.42
     onItemClick
    0.42
    acic
    0.41
    richTextPanel
    0.41
    Act Density 0.001%

    No Known Activations