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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks used to indicate transitions or contrasts

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

    punctuation and section dividers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.31
    ReusableCell
    -0.31
     gend
    -0.30
     iNdEx
    -0.29
    migrationBuilder
    -0.29
     elif
    -0.29
     unknownFields
    -0.29
     inger
    -0.29
     farma
    -0.27
    Wave
    -0.27
    POSITIVE LOGITS
     '\\;'
    0.74
     defaultstate
    0.63
     otomatig
    0.59
    Referències
    0.56
    Izvori
    0.55
    Viitteet
    0.55
    awtextra
    0.54
    ⓧ
    0.54
    ibatkan
    0.54
     ivelany
    0.53
    Act Density 0.154%

    No Known Activations