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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation or special characters that indicate distinctions in the text

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

    form the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    -0.33
    NSIndexPath
    -0.31
     Audiodateien
    -0.30
    </h4>
    -0.29
    .
    -0.29
    -
    -0.28
     etc
    -0.27
     investigador
    -0.27
     Researchers
    -0.26
     and
    -0.25
    POSITIVE LOGITS
    IndentedString
    0.78
    <unused23>
    0.75
    <unused41>
    0.75
    <unused14>
    0.75
    <unused17>
    0.75
    <unused42>
    0.74
    <unused51>
    0.74
    <unused28>
    0.74
    [@BOS@]
    0.74
    <unused16>
    0.74
    Act Density 0.104%

    No Known Activations