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

    Neuronpedia

    INDEX
    Explanations

    python class initialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     furthest
    0.83
     fooled
    0.82
     farthest
    0.80
     thrilled
    0.79
     pupils
    0.75
     stunned
    0.74
     dearest
    0.74
     (_,
    0.73
     glad
    0.72
     fortunate
    0.70
    POSITIVE LOGITS
    机器学习
    0.94
    Invest
    0.90
     निवेश
    0.87
     diffeomorphism
    0.85
     Supernatural
    0.84
    也会
    0.82
     también
    0.82
    Genero
    0.81
    也會
    0.81
    Connection
    0.80
    Act Density 0.059%

    No Known Activations