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

    Neuronpedia

    INDEX
    Explanations

    specific character names and their associated traits or attributes

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

    names, titles, or labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.54
     utafitiHapana
    -0.52
    awtextra
    -0.51
     Christendom
    -0.49
    DotNetBar
    -0.47
     surla
    -0.47
    UserScript
    -0.47
    uxxxx
    -0.46
    Földrajzportál
    -0.46
    Дорогие
    -0.45
    POSITIVE LOGITS
    tinyos
    0.41
    halb
    0.38
    ().__
    0.36
    seende
    0.36
    🐾
    0.34
    cnia
    0.31
     Suprema
    0.31
    WithIOException
    0.31
    NOP
    0.30
    */),
    0.30
    Act Density 0.002%

    No Known Activations