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

    Neuronpedia

    INDEX
    Explanations

    code/markup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :::::
    -0.06
     Minuten
    -0.06
    .bc
    -0.06
    _interface
    -0.06
    .Interop
    -0.06
    丈
    -0.06
     eben
    -0.06
    諾
    -0.06
    Ul
    -0.06
     кг
    -0.06
    POSITIVE LOGITS
     Tar
    0.07
    (forKey
    0.07
     reb
    0.07
    .preventDefault
    0.06
    駅
    0.06
     caric
    0.06
     slice
    0.06
     orient
    0.06
     suction
    0.06
    ransition
    0.06
    Act Density 0.033%

    No Known Activations