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

    Neuronpedia

    INDEX
    Explanations

    Motors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.80
     autorytatywna
    -0.75
    ########.
    -0.73
    LookAnd
    -0.70
    :✨
    -0.62
    principalColumn
    -0.62
    RepeatedField
    -0.62
    fromnode
    -0.60
    Rhestr
    -0.59
    Erreferentziak
    -0.59
    POSITIVE LOGITS
    ’
    0.61
    <bos>
    0.55
     simplifié
    0.53
    '
    0.53
     movers
    0.50
     labs
    0.49
     –
    0.49
     adults
    0.48
     injections
    0.48
     laboratories
    0.48
    Act Density 0.077%

    No Known Activations