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

    Neuronpedia

    INDEX
    Explanations

    run

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     controller
    -0.07
    人は
    -0.06
     ап
    -0.06
     shepherd
    -0.06
     Glacier
    -0.06
    Wars
    -0.06
    通过
    -0.06
     pipe
    -0.06
     ass
    -0.06
     pipeline
    -0.06
    POSITIVE LOGITS
     Running
    0.08
    競
    0.07
    .initState
    0.07
     Друг
    0.07
    _ret
    0.07
     jogging
    0.07
     running
    0.07
    .goto
    0.07
     Run
    0.07
    ennis
    0.07
    Act Density 0.008%

    No Known Activations