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

    Neuronpedia

    INDEX
    Explanations

    running and related activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    钣
    0.71
    傀
    0.68
     Toxicity
    0.64
    toxicity
    0.64
    ገል
    0.63
    ত্তির
    0.62
    ∝
    0.62
    ണ്ഡി
    0.61
    adne
    0.60
    𓂀
    0.60
    POSITIVE LOGITS
     runners
    3.36
     running
    3.33
     Running
    3.26
     runner
    3.21
    Running
    3.17
     Runners
    3.08
    running
    3.08
     Runner
    3.01
    Run
    2.98
     run
    2.97
    Act Density 0.238%

    No Known Activations