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

    Neuronpedia

    INDEX
    Explanations

    monetary values related to debts or financial obligations

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

    numbers and "line"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Савезне
    -0.59
    majánló
    -0.56
    endregion
    -0.56
     パンチラ
    -0.54
    parsedMessage
    -0.54
    <unused41>
    -0.53
    <unused17>
    -0.52
    <unused28>
    -0.52
    <unused14>
    -0.52
    [@BOS@]
    -0.52
    POSITIVE LOGITS
    ConstraintMaker
    0.56
     indeed
    0.32
    期刊论文
    0.31
     󰀄
    0.30
     completos
    0.30
     totalidad
    0.30
    miljø
    0.30
     […]
    0.29
     ***!
    0.29
     nią
    0.29
    Act Density 0.030%

    No Known Activations