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

    Neuronpedia

    INDEX
    Explanations

    employment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.80
    ResponseWriter
    -0.77
    Хьажоргаш
    -0.76
    ]--;
    -0.75
     myſelf
    -0.75
     Reſ
    -0.71
     iſt
    -0.71
     reaſon
    -0.69
    Diwedd
    -0.69
     ſtate
    -0.69
    POSITIVE LOGITS
     of
    0.93
     concernés
    0.66
    e
    0.57
    s
    0.57
     bonheur
    0.55
     from
    0.53
     fratelli
    0.52
    <h5>
    0.52
     to
    0.51
     for
    0.51
    Act Density 0.802%

    No Known Activations