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

    Neuronpedia

    INDEX
    Explanations

    actions related to maintenance and ongoing attention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    keeping something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.47
    Xna
    -0.40
    setOnAction
    -0.35
    monix
    -0.35
     partnered
    -0.34
    RectangleBorder
    -0.34
    odule
    -0.34
     longer
    -0.34
     ujednoznacz
    -0.34
    woosh
    -0.34
    POSITIVE LOGITS
    Keep
    0.64
    keeps
    0.63
     keeps
    0.62
    keep
    0.61
     Keeping
    0.60
     Keep
    0.58
    KEEP
    0.58
    Keeping
    0.58
     Keeps
    0.57
    Keeps
    0.57
    Act Density 0.016%

    No Known Activations