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

    Neuronpedia

    INDEX
    Explanations

    sequences of whitespace or indentation in code

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

    rows containing 0’s

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     informée
    -0.55
     препратки
    -0.51
    invokeLater
    -0.49
    raborty
    -0.47
    Autoritní
    -0.46
     استنادى
    -0.42
     doInBackground
    -0.41
    #+#
    -0.40
     perchè
    -0.39
    Revenir
    -0.39
    POSITIVE LOGITS
     étoit
    0.53
     ſeveral
    0.52
     Anſ
    0.52
     sánchez
    0.50
     gonzález
    0.50
     Perſ
    0.50
     ſont
    0.49
     ſmall
    0.49
     queſta
    0.49
     greateſt
    0.48
    Act Density 0.105%

    No Known Activations