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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Europeans
    -0.68
     mainland
    -0.68
    loo
    -0.66
    atives
    -0.64
    ative
    -0.63
    Bay
    -0.63
    anos
    -0.62
     Poles
    -0.61
    Primary
    -0.61
    Capital
    -0.61
    POSITIVE LOGITS
    reprene
    0.71
    ening
    0.70
     [&
    0.67
    aceous
    0.66
    rir
    0.65
     âĩ
    0.65
    yg
    0.62
    fram
    0.62
    oult
    0.62
     syrup
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.