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

    Neuronpedia

    INDEX
    Explanations

    references to data structures or formats

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

    Characters followed by seemingly random strings

    np_acts-logits-general · gemini-2.0-flash

    tokens after specific tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.60
     Seeder
    -0.59
     okuyayım
    -0.58
    DeleteBehavior
    -0.58
    enterOuterAlt
    -0.53
    orianCalendar
    -0.52
    pragma
    -0.50
    twimg
    -0.50
    >{@
    -0.50
    iedy
    -0.49
    POSITIVE LOGITS
    出版年
    0.61
    nito
    0.54
     lordship
    0.54
     Esau
    0.53
     Virol
    0.52
     Stowe
    0.51
    rents
    0.51
     Hopf
    0.51
    ness
    0.49
     Patro
    0.49
    Act Density 0.030%

    No Known Activations