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

    Neuronpedia

    INDEX
    Explanations

    sentences that describe characteristics or features

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

    is that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.56
    IndentedString
    -0.56
    цездатний
    -0.48
     kasarigan
    -0.44
     iNdEx
    -0.43
    addContainerGap
    -0.42
    بوابة
    -0.42
     GetEnumerator
    -0.42
    Jereo
    -0.41
    PositiveButton
    -0.40
    POSITIVE LOGITS
     surla
    0.51
     gæ
    0.46
    setVerticalGroup
    0.44
     türlü
    0.41
     المعيارى
    0.41
    saraba
    0.40
    retention
    0.40
     snippetHide
    0.40
    Mainly
    0.40
     näky
    0.40
    Act Density 0.171%

    No Known Activations