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

    Neuronpedia

    INDEX
    Explanations

    Cleaning/surface interaction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    句话
    -0.07
     Along
    -0.06
     Should
    -0.06
    (Source
    -0.06
    -mouth
    -0.06
    OA
    -0.06
    plete
    -0.06
    ipients
    -0.06
     otra
    -0.06
     cabbage
    -0.06
    POSITIVE LOGITS
    گونه
    0.07
    €“
    0.07
    ζα
    0.06
    ukkit
    0.06
    licts
    0.06
    -toggler
    0.06
    RDD
    0.06
     администра
    0.06
    yii
    0.06
     Scout
    0.06
    Act Density 0.073%

    No Known Activations