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

    Neuronpedia

    INDEX
    Explanations

    characters in URLs for youtube.com

    oai_token-act-pair · gemini-2.0-flash

    URLs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     виправивши
    -0.74
     فريبيس
    -0.71
    Autoritní
    -0.69
     InputDecoration
    -0.66
    Rhestr
    -0.65
    aarrggbb
    -0.65
     autorytatywna
    -0.65
    +#+#
    -0.65
    ollectionView
    -0.64
    yntaxException
    -0.64
    POSITIVE LOGITS
     virš
    0.49
    -
    0.45
     adulte
    0.44
    3
    0.44
    を迎
    0.43
    ArgumentParser
    0.42
     drawn
    0.42
    ала
    0.42
     addi
    0.41
    giveness
    0.41
    Act Density 0.403%

    No Known Activations