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

    Neuronpedia

    INDEX
    Explanations

    the word "underlying"

    oai_token-act-pair · gemini-2.0-flash

    underlying

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.77
    <bos>
    -0.75
    Rüyada
    -0.69
    fjspx
    -0.68
    ftagPool
    -0.66
    )':
    -0.64
    profen
    -0.64
    ConstraintMaker
    -0.63
    SwingConstants
    -0.63
    发表于
    -0.62
    POSITIVE LOGITS
     igjen
    0.72
     étrangères
    0.71
     liitty
    0.70
     verkligen
    0.69
    kepada
    0.69
     gärna
    0.68
     hendes
    0.68
     gång
    0.68
     kesan
    0.66
     sportivo
    0.66
    Act Density 0.919%

    No Known Activations