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

    Neuronpedia

    INDEX
    Explanations

    URLs and mentions of news outlets or stories

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

    crown court, mirror, record, ledger, celebrity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tikang
    -0.75
    ReusableCell
    -0.75
    AndEndTag
    -0.69
    setVerticalGroup
    -0.69
    yarnpkg
    -0.69
    <unused14>
    -0.66
    <unused17>
    -0.66
    <unused8>
    -0.66
    <pad>
    -0.66
    <unused3>
    -0.66
    POSITIVE LOGITS
    News
    0.30
    slice
    0.28
     Kuz
    0.28
    .
    0.28
    '
    0.28
    ↵↵
    0.28
    Vir
    0.27
    K
    0.27
    ax
    0.27
    <
    0.26
    Act Density 0.031%

    No Known Activations