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

    Neuronpedia

    INDEX
    Explanations

    artistic experimentation and exploration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bonuses
    0.54
     PUBG
    0.52
     tweeted
    0.45
     Bonuses
    0.45
     COUNT
    0.45
     improvements
    0.45
     экспер
    0.44
    circledR
    0.44
     HUOBI
    0.44
    陪
    0.44
    POSITIVE LOGITS
     sculptural
    0.83
     experimentation
    0.78
     experimenting
    0.77
     exploring
    0.70
     explorar
    0.68
     textural
    0.68
     speriment
    0.66
     explore
    0.64
     explorations
    0.64
     alchemy
    0.64
    Act Density 0.023%

    No Known Activations