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

    Neuronpedia

    INDEX
    Explanations

    day

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _models
    -0.07
    辜
    -0.07
    刊
    -0.07
    退休
    -0.07
    阔
    -0.06
    美丽
    -0.06
    EAR
    -0.06
     gek
    -0.06
    TouchableOpacity
    -0.06
     dz
    -0.06
    POSITIVE LOGITS
    .RowHeaders
    0.07
    people
    0.07
    .big
    0.07
     wouldn
    0.07
     Ones
    0.07
     relevance
    0.07
     riders
    0.06
    Do
    0.06
    太多
    0.06
    .Payload
    0.06
    Act Density 0.042%

    No Known Activations