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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    adays
    -0.09
    گ
    -0.07
     wild
    -0.07
    ursion
    -0.07
     Correspond
    -0.07
     photograph
    -0.07
    摄影作品
    -0.06
    Escape
    -0.06
     kindly
    -0.06
    ackets
    -0.06
    POSITIVE LOGITS
     illicit
    0.07
    怩
    0.07
    \">";↵
    0.07
    Svc
    0.07
    ())
↵
    0.06
    让他们
    0.06
     Aub
    0.06
     혹은
    0.06
     Lighting
    0.06
    bió
    0.06
    Act Density 0.001%

    No Known Activations