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

    Neuronpedia

    INDEX
    Explanations

    words and phrases involved in planning events

    oai_token-act-pair · gemini-2.0-flash

    taking actions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spesa
    -0.53
     WebDriverWait
    -0.53
     rospy
    -0.52
    허
    -0.50
     Kirch
    -0.48
    jero
    -0.47
    ąt
    -0.47
    贛
    -0.46
     anello
    -0.46
     AppColors
    -0.45
    POSITIVE LOGITS
     BoxFit
    0.65
    Билгалдахарш
    0.62
    Искәрмәләр
    0.61
     متعلقه
    0.58
     виправивши
    0.56
    ัติ
    0.56
     IndexPath
    0.56
    nologue
    0.56
    ')['
    0.54
    Expedia
    0.52
    Act Density 1.895%

    No Known Activations