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

    Neuronpedia

    INDEX
    Explanations

    generic whitespace tokens or separators in the text

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

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.77
     Савезне
    -0.77
    UnusedPrivate
    -0.75
    WebElementEntity
    -0.72
    IVEREF
    -0.66
    новниш
    -0.65
     виправивши
    -0.65
    sizeCache
    -0.65
     beginnetje
    -0.64
    /*++
    -0.61
    POSITIVE LOGITS
     termica
    0.43
    heim
    0.41
    mathrm
    0.41
     obicei
    0.41
     eddy
    0.39
    ’
    0.39
    IDAY
    0.37
    ufs
    0.37
    телна
    0.36
    <tbody>
    0.36
    Act Density 0.265%

    No Known Activations