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

    Neuronpedia

    INDEX
    Explanations

    occurrences of special characters and symbols, particularly accented letters and HTML entities

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

    encoding errors and special characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     незавершена
    -0.56
     lup
    -0.54
    InputBorder
    -0.53
     -$
    -0.53
    urtstag
    -0.52
    endpush
    -0.52
     okuyayım
    -0.52
    enderror
    -0.52
     -'
    -0.49
     dAtA
    -0.49
    POSITIVE LOGITS
    â
    1.41
     â
    0.71
    lâ
    0.63
    Â
    0.59
    Ã
    0.59
    câ
    0.56
    вЂ
    0.53
     Câ
    0.51
    Câ
    0.51
    &#
    0.47
    Act Density 0.016%

    No Known Activations