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

    Neuronpedia

    INDEX
    Explanations

    Run: Open

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tooltip
    0.80
    Dockerfile
    0.80
     Grizz
    0.77
    click
    0.76
    Tooltip
    0.76
    select
    0.73
    upstream
    0.72
    èi
    0.71
    点击
    0.70
    wg
    0.69
    POSITIVE LOGITS
     Runs
    0.75
     CD
    0.73
     varied
    0.71
     Run
    0.68
     Mientras
    0.67
     aerodynamics
    0.66
     running
    0.64
     Final
    0.63
     Running
    0.63
     marketers
    0.63
    Act Density 0.067%

    No Known Activations