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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     hypersurfaces
    1.01
    𝜌
    0.97
     ángulos
    0.96
    𓏧
    0.95
     bilinear
    0.95
     dolom
    0.95
     columnas
    0.92
     データ
    0.92
     phonons
    0.91
     mivel
    0.91
    POSITIVE LOGITS
    '
    1.07
    '.
    0.80
    .'
    0.80
    0.80
    GA
    0.80
    .
    0.79
    eg
    0.76
    -
    0.75
    ↵↵
    0.71
    WE
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.