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

    Neuronpedia

    INDEX
    Explanations

    run or execute code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    表記
    0.62
    籮
    0.62
    ardu
    0.60
     refor
    0.60
     probing
    0.59
     encroach
    0.59
    addies
    0.59
     decommission
    0.59
    情報は
    0.58
    ouchement
    0.57
    POSITIVE LOGITS
     Run
    2.52
    Run
    2.51
     run
    2.50
     execute
    2.40
     execution
    2.38
     Execute
    2.36
    run
    2.36
    実行
    2.30
     Execution
    2.28
    Execute
    2.26
    Act Density 0.677%

    No Known Activations