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

    Neuronpedia

    INDEX
    Explanations

    specific medical or scientific terms and their implications

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

    Tokens followed by parentheses

    np_acts-logits-general · gemini-2.0-flash

    opening parenthesis or quote

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estekak
    -1.00
    writeFieldEnd
    -0.91
    存于互联网档案馆
    -0.88
     للاسماء
    -0.87
     AssemblyTitle
    -0.85
     الرياضيه
    -0.85
    WithIOException
    -0.84
     تانيه
    -0.83
     */
    -0.81
    хьтан
    -0.77
    POSITIVE LOGITS
     (
    1.82
    （
    1.30
     (=
    1.15
     ("
    1.07
     (“
    1.06
     yani
    1.03
     （
    1.03
    (
    1.02
     [
    1.00
     (‘
    0.99
    Act Density 0.592%

    No Known Activations