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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and symbols related to negative values or decay processes

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

    negatively charged

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WireFormatLite
    -0.60
    sizeCache
    -0.57
     ComVisible
    -0.50
    SceneManagement
    -0.49
     estekak
    -0.48
    inflate
    -0.48
    تقاوى
    -0.48
    IUrlHelper
    -0.48
    存于互联网档案馆
    -0.47
    awtextra
    -0.47
    POSITIVE LOGITS
     down
    0.70
     lowering
    0.65
     downward
    0.63
     downwards
    0.60
    down
    0.59
     herunter
    0.58
     DOWN
    0.57
     Down
    0.57
     runter
    0.55
     lower
    0.54
    Act Density 0.394%

    No Known Activations