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

    Neuronpedia

    INDEX
    Explanations

    references to collective actions and community engagement

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

    we, our

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    readLine
    -0.37
     '\\;'
    -0.37
     فريبيس
    -0.35
     للمعارف
    -0.35
     kasarigan
    -0.34
     XCTest
    -0.33
     gambe
    -0.32
    bkz
    -0.32
    ёх
    -0.31
     subsequent
    -0.31
    POSITIVE LOGITS
    mbggenerated
    0.57
     ब्रेकडाउन
    0.54
    Présentation
    0.53
    Celebrating
    0.53
    Promoting
    0.51
    Community
    0.50
    Glory
    0.50
     defaultstate
    0.48
    celebr
    0.48
     clô
    0.47
    Act Density 0.023%

    No Known Activations