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

    Neuronpedia

    INDEX
    Explanations

    Taylor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    elfare
    -0.57
    WriteTagHelper
    -0.56
    )]{
    -0.56
    ztály
    -0.51
    </thead>
    -0.51
    Especially
    -0.49
     slightest
    -0.49
     Especially
    -0.48
    .³
    -0.47
    ATIVA
    -0.46
    POSITIVE LOGITS
    <bos>
    0.84
     ویکی‌پدیا
    0.67
     nahilalakip
    0.65
    DockStyle
    0.61
    ’
    0.60
     pelea
    0.58
    __((
    0.58
    ioutil
    0.58
     nakalista
    0.57
     AssemblyCulture
    0.56
    Act Density 0.000%

    No Known Activations