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

    Neuronpedia

    INDEX
    Explanations

    patterns of whitespace or indentation in code blocks

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

    Code or programming-related text

    np_acts-logits-general · gemini-2.0-flash

    programming code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Durchsch
    -0.32
    lotz
    -0.29
     없습니다
    -0.28
     '{@
    -0.28
     since
    -0.28
     Abonnez
    -0.27
     
    -0.27
     sobremesa
    -0.27
     azule
    -0.26
    ngdoc
    -0.26
    POSITIVE LOGITS
     FontWeight
    0.97
     メンテナ
    0.84
    <unused41>
    0.84
    <unused14>
    0.83
     tartalo
    0.83
    <unused8>
    0.83
    <unused23>
    0.83
    <unused74>
    0.83
    <unused28>
    0.83
    <pad>
    0.83
    Act Density 0.013%

    No Known Activations