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

    Neuronpedia

    INDEX
    Explanations

    data and datasets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    愜
    0.47
    üle
    0.46
     majest
    0.46
    高兴
    0.44
     flamboyant
    0.44
     templo
    0.43
    语气
    0.43
     തോന്ന
    0.42
    审美
    0.42
     BlueprintName
    0.42
    POSITIVE LOGITS
     data
    1.36
     datasets
    1.32
    data
    1.25
     dataset
    1.19
     Data
    1.13
    データ
    1.06
     डेटा
    1.06
    Data
    1.05
    数据
    1.05
     DATA
    1.02
    Act Density 0.684%

    No Known Activations