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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "drop" in different contexts

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

    "drop" or "dropped"

    np_acts-logits-general · gemini-2.0-flash

    drop-down or dropped out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UnitTesting
    -0.63
    usitis
    -0.55
     Дата
    -0.54
    createCanvas
    -0.54
    atians
    -0.54
    QMetaType
    -0.52
    XmlAccessorType
    -0.51
    enumerate
    -0.51
     ***!
    -0.50
    gesi
    -0.50
    POSITIVE LOGITS
     drop
    1.46
    drop
    1.42
     Drop
    1.41
     drops
    1.41
    drops
    1.38
    Drop
    1.33
     DROP
    1.31
     dropping
    1.29
     dropped
    1.29
     Drops
    1.28
    Act Density 0.077%

    No Known Activations