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

    Neuronpedia

    INDEX
    Explanations

    code generation and writing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    renamiento
    0.46
    Appeal
    0.45
    విద్య
    0.44
    Би
    0.43
    Learning
    0.43
    Feeling
    0.43
    apunov
    0.43
    विद्यालय
    0.42
    Visualization
    0.42
    }=$
    0.42
    POSITIVE LOGITS
     OEMs
    0.58
     smoothies
    0.55
     streetwear
    0.53
     standalone
    0.51
     dashboards
    0.51
     Durable
    0.50
     restrooms
    0.50
     snapshots
    0.48
     markets
    0.48
     frees
    0.47
    Act Density 0.002%

    No Known Activations