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

    Neuronpedia

    INDEX
    Explanations

    function calls related to clearing or resetting objects or values

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

    clearing things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     adventure
    -0.58
     onView
    -0.56
     rospy
    -0.50
     sociétés
    -0.50
     htons
    -0.50
     elif
    -0.49
     humer
    -0.48
     jsonObj
    -0.48
     adventures
    -0.48
     eventId
    -0.48
    POSITIVE LOGITS
    Clear
    0.84
    clear
    0.82
     Clear
    0.82
     clearing
    0.73
    cleared
    0.72
     clears
    0.71
    clearing
    0.71
     Clearing
    0.69
    Clearing
    0.69
     clear
    0.68
    Act Density 0.007%

    No Known Activations