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

    Neuronpedia

    INDEX
    Explanations

    movement/direction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Gatt
    -0.07
    pq
    -0.06
    [MAX
    -0.06
    RAW
    -0.06
    ฟอร
    -0.06
    .Lo
    -0.06
    ではなく
    -0.06
     PureComponent
    -0.06
    leveland
    -0.06
    .red
    -0.06
    POSITIVE LOGITS
     Canterbury
    0.07
    <Transform
    0.06
     apology
    0.06
     implementing
    0.06
     squeezed
    0.06
     episodes
    0.06
    ectar
    0.06
    ebilirsiniz
    0.06
    aliases
    0.06
    еро
    0.06
    Act Density 0.003%

    No Known Activations