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

    Neuronpedia

    INDEX
    Explanations

    pairs of letters

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.69
    principalColumn
    -0.63
    GenerationType
    -0.63
     traditionnels
    -0.62
     fidé
    -0.62
    diğini
    -0.60
    انتهای
    -0.59
     publicitaires
    -0.58
    UnusedPrivate
    -0.57
     fisuras
    -0.57
    POSITIVE LOGITS
     been
    0.77
     be
    0.72
    been
    0.68
     AssemblyVersion
    0.59
     Been
    0.59
    évaluateur
    0.59
     have
    0.58
     povezave
    0.56
    Been
    0.56
     Be
    0.55
    Act Density 0.687%

    No Known Activations