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

    Neuronpedia

    INDEX
    Explanations

    comparing data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     amore
    -0.07
     understood
    -0.07
     fie
    -0.07
     Document
    -0.07
     wondered
    -0.07
     pulled
    -0.07
     Constructors
    -0.06
    Video
    -0.06
    Figure
    -0.06
    EE
    -0.06
    POSITIVE LOGITS
    告诉她
    0.09
    enemy
    0.07
     Formatting
    0.07
     neuen
    0.07
     gdyż
    0.07
    <<<<<<<
    0.07
    蚬
    0.07
     giants
    0.07
    转弯
    0.07
    hive
    0.07
    Act Density 0.002%

    No Known Activations