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

    Neuronpedia

    INDEX
    Explanations

    references to mystical or supernatural elements

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

    erased history, despair, sanity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RTLU
    -0.69
    richTextPanel
    -0.65
    queryInterface
    -0.64
    تقاوى
    -0.63
    IBLIO
    -0.61
    RegressionTest
    -0.60
    WebServlet
    -0.60
     myſelf
    -0.59
    delwed
    -0.58
    __(/*!
    -0.58
    POSITIVE LOGITS
     cognitive
    0.36
     humans
    0.36
     cognition
    0.35
     pro
    0.32
     pró
    0.31
     propa
    0.31
     fa
    0.30
     human
    0.30
     ter
    0.30
     causes
    0.30
    Act Density 0.068%

    No Known Activations