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

    Neuronpedia

    INDEX
    Explanations

    programming assignment statements and initialization expressions

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

    length of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.62
    UserScript
    -0.60
    ſelf
    -0.58
     Houſe
    -0.57
    <unused41>
    -0.56
    <unused14>
    -0.56
    [@BOS@]
    -0.56
    <unused23>
    -0.56
    <unused17>
    -0.56
    <unused8>
    -0.56
    POSITIVE LOGITS
    setViewportView
    0.33
    帖最后由
    0.32
     sterren
    0.30
     jakie
    0.28
     aient
    0.28
    ızlık
    0.28
    りに
    0.28
    ><?
    0.28
    writeFieldEnd
    0.28
    sy
    0.27
    Act Density 0.008%

    No Known Activations