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

    Neuronpedia

    INDEX
    Explanations

    game scripting languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     compiler
    0.84
     trout
    0.79
     fisherman
    0.78
     compile
    0.76
     fishing
    0.76
     mes
    0.74
     mas
    0.73
     sno
    0.71
    LED
    0.69
     बेव
    0.69
    POSITIVE LOGITS
     Roblox
    1.10
     openai
    0.93
    🧒
    0.86
    🥉
    0.85
    blox
    0.84
    叕
    0.84
     DeSantis
    0.83
    Archer
    0.82
    openai
    0.82
    cognitive
    0.82
    Act Density 0.032%

    No Known Activations