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

    Neuronpedia

    INDEX
    Explanations

    sequences of whitespace characters or empty lines

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

    code punctuation and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     DBNull
    -0.40
     desmotivaciones
    -0.37
     roleId
    -0.35
     refroid
    -0.35
     sanitaires
    -0.34
     HasFactory
    -0.34
     debilidad
    -0.34
     destinées
    -0.33
    一張
    -0.32
     militaires
    -0.32
    POSITIVE LOGITS
     كومونز
    0.81
    `,
    0.61
    ',
    0.60
    ',
    0.59
     يتيمه
    0.57
    $",
    0.56
    (
    0.56
    "][
    0.54
    :");
    0.53
    ...");
    0.52
    Act Density 0.017%

    No Known Activations