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

    Neuronpedia

    INDEX
    Explanations

    ones

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ones
    -1.81
     those
    -1.28
     ceux
    -0.98
    Those
    -0.95
    those
    -0.95
     quelli
    -0.95
     Those
    -0.93
     Ones
    -0.93
    那些
    -0.92
     thoſe
    -0.88
    POSITIVE LOGITS
    '
    0.67
     of
    0.63
    .
    0.59
    -
    0.59
     powi
    0.52
    `
    0.50
    Wass
    0.49
     petitioned
    0.49
    ’
    0.49
     Portuguesa
    0.48
    Act Density 0.012%

    No Known Activations