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

    Neuronpedia

    INDEX
    Explanations

    Averages and units

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    manageable
    -0.08
     manageable
    -0.08
     Costa
    -0.08
    Leaf
    -0.08
    minster
    -0.08
     consegue
    -0.07
    bahn
    -0.07
     Slov
    -0.07
    דז
    -0.07
     buds
    -0.07
    POSITIVE LOGITS
     variability
    0.11
     deviation
    0.11
    _average
    0.10
    Deviation
    0.10
     avg
    0.10
    _avg
    0.10
     deviations
    0.10
    verages
    0.10
    平均
    0.09
     평균
    0.09
    Act Density 0.068%

    No Known Activations