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

    Neuronpedia

    INDEX
    Explanations

    references to specific elements or terms in user interface instructions

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

    UI element interactions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    awtextra
    -0.71
     चीज़ों
    -0.64
    -0.58
    Билгалдахарш
    -0.57
    PyExc
    -0.56
     MainAxisSize
    -0.56
     للاسماء
    -0.56
    AndroidJUnit
    -0.54
    ENOMEM
    -0.53
     CommonModule
    -0.51
    POSITIVE LOGITS
     button
    0.55
     box
    0.54
     buttons
    0.49
     label
    0.48
     link
    0.47
     boxes
    0.46
     logo
    0.45
     below
    0.45
     regular
    0.44
     rubrique
    0.44
    Act Density 0.014%

    No Known Activations