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

    Neuronpedia

    INDEX
    Explanations

    Restriction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    restricted
    -0.82
     encompassing
    -0.79
    Restricted
    -0.76
     Restricted
    -0.72
     Restriction
    -0.67
     restricted
    -0.65
     covering
    -0.65
    restriction
    -0.64
     restriction
    -0.63
     restricting
    -0.61
    POSITIVE LOGITS
    Personendaten
    0.69
     Réponses
    0.67
     ujednoznacz
    0.65
    ly
    0.62
    RenderAtEndOf
    0.59
    تقاوى
    0.59
    subplots
    0.58
     synonyms
    0.58
    basicConfig
    0.58
    Rüyada
    0.58
    Act Density 0.067%

    No Known Activations