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

    Neuronpedia

    INDEX
    Explanations

    references to different models of products or vehicles

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

    model followed by specific noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     respectivamente
    -0.49
     süre
    -0.47
     boyunca
    -0.43
     vuoi
    -0.43
     terang
    -0.43
     calzado
    -0.42
     tajam
    -0.41
     bezpiecze
    -0.41
     dovre
    -0.40
     precisam
    -0.40
    POSITIVE LOGITS
     Model
    1.20
     MODEL
    0.99
     model
    0.96
    Model
    0.85
    MODEL
    0.82
    model
    0.80
     Modell
    0.79
     Models
    0.77
     модель
    0.75
     Modelo
    0.71
    Act Density 0.021%

    No Known Activations