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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.85
    interopRequire
    -0.83
    вгений
    -0.73
     autorytatywna
    -0.67
     varandra
    -0.65
    piecze
    -0.64
    Datuak
    -0.63
     Савез
    -0.62
    archiviato
    -0.61
    %")
    -0.61
    POSITIVE LOGITS
    Rüyada
    0.58
     optionally
    0.53
    <eos>
    0.50
    ник
    0.48
    WebElementEntity
    0.47
    lehrer
    0.46
     or
    0.46
    Lexer
    0.45
     digress
    0.45
    eleste
    0.44
    Act Density 0.208%

    No Known Activations