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

    Neuronpedia

    INDEX
    Explanations

    repeated actions or occurrences

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

    actions repeated or run

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    writeFieldEnd
    -0.39
     مها
    -0.29
     Tats
    -0.29
     pickles
    -0.28
     Wea
    -0.27
    쇠
    -0.27
    üyü
    -0.27
    kissen
    -0.27
     morceau
    -0.26
     antig
    -0.26
    POSITIVE LOGITS
    yntaxException
    0.57
    InjectAttribute
    0.53
    BufferException
    0.52
     Bertram
    0.49
     Biôgrafia
    0.49
     TestBed
    0.48
    httphttps
    0.47
    Бахар
    0.47
     replay
    0.47
     repeat
    0.47
    Act Density 0.053%

    No Known Activations