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

    Neuronpedia

    INDEX
    Explanations

    excited

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exciting
    -0.56
     excitedly
    -0.52
     excited
    -0.46
     excites
    -0.46
    зулта
    -0.45
    excited
    -0.44
     emphasis
    -0.43
    Exciting
    -0.43
    hot
    -0.43
    ObjectContext
    -0.42
    POSITIVE LOGITS
     ब्रेकडाउन
    0.84
    </caption>
    0.79
     tartalomajánló
    0.74
     ainfi
    0.73
    MLLoader
    0.69
     automatiques
    0.68
    extAlignment
    0.67
    脚注の使い方
    0.65
    IntoConstraints
    0.65
     disambiguazione
    0.65
    Act Density 0.013%

    No Known Activations