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

    Neuronpedia

    INDEX
    Explanations

    words signifying high quality judgement and positive traits

    oai_token-act-pair · gemini-2.0-flash

    reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.88
    '
    -0.62
    ↵↵
    -0.55
    I
    -0.55
    s
    -0.54
     the
    -0.48
    n
    -0.47
     I
    -0.45
     and
    -0.44
    ↵
    -0.43
    POSITIVE LOGITS
    IndentedString
    1.16
    +#+#
    1.09
     ddelweddau
    1.08
     lenker
    0.98
     виправивши
    0.96
    protoimpl
    0.94
     autorytatywna
    0.94
     resourceCulture
    0.91
     estekak
    0.88
    InputBorder
    0.88
    Act Density 0.878%

    No Known Activations