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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.77
    <_>
    -0.65
    endphp
    -0.65
     waste
    -0.64
     ComVisible
    -0.62
     drag
    -0.61
     vuitton
    -0.60
     Efq
    -0.59
    autique
    -0.59
    PreferredItem
    -0.59
    POSITIVE LOGITS
     kasarigan
    0.70
    脚注の使い方
    0.53
     evolve
    0.53
    KommentareTeilen
    0.52
     shape
    0.52
    TintMode
    0.50
    CloseOperation
    0.50
    <bos>
    0.47
    shape
    0.46
    ?}",
    0.46
    Act Density 0.009%

    No Known Activations