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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Chip
    -0.07
     gegenüber
    -0.07
     contestants
    -0.07
    🥓
    -0.07
     Noticed
    -0.07
    稳定性
    -0.07
     луч
    -0.06
     آ
    -0.06
    zs
    -0.06
     최
    -0.06
    POSITIVE LOGITS
     workflow
    0.07
    uteur
    0.07
    SKU
    0.07
    nge
    0.07
     Fayette
    0.06
     WRITE
    0.06
     hectares
    0.06
    퓔
    0.06
    Goals
    0.06
    吸引更多
    0.06
    Act Density 0.000%

    No Known Activations