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

    Neuronpedia

    INDEX
    Explanations

    references to code structure and definitions

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

    LL or <<

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UnusedPrivate
    -0.56
    transQ
    -0.52
     informée
    -0.49
     насељу
    -0.49
    Composable
    -0.48
    Tikang
    -0.47
    存于互联网档案馆
    -0.47
    الحياه
    -0.47
    SequentialGroup
    -0.47
     Apostolic
    -0.46
    POSITIVE LOGITS
     LL
    0.50
     ll
    0.47
    ll
    0.46
    oyd
    0.45
    oy
    0.40
    LL
    0.40
    lysses
    0.40
     Ull
    0.38
     ILogger
    0.36
    Biographie
    0.36
    Act Density 0.006%

    No Known Activations