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

    Neuronpedia

    INDEX
    Explanations

    verdict

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pond
    -0.08
    .toolbar
    -0.07
    不予
    -0.07
    gun
    -0.07
     Mare
    -0.07
    .Generation
    -0.07
     Cater
    -0.07
    Outside
    -0.07
    眼前
    -0.07
     Bunny
    -0.07
    POSITIVE LOGITS
    漷
    0.07
    视频
    0.07
    filter
    0.07
    Get
    0.07
    posted
    0.06
    ainted
    0.06
     saved
    0.06
     דיגיטלי
    0.06
     V
    0.06
     wirklich
    0.06
    Act Density 0.001%

    No Known Activations