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

    Neuronpedia

    INDEX
    Explanations

    non-English

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    енной
    -0.07
     حذف
    -0.07
     çıkart
    -0.06
    (pi
    -0.06
     BUILD
    -0.06
     Procedures
    -0.06
    .absolute
    -0.06
     perfor
    -0.06
     ANAL
    -0.06
     hale
    -0.06
    POSITIVE LOGITS
     health
    0.07
    igits
    0.07
     server
    0.07
     africa
    0.06
     }
↵
    0.06
    region
    0.06
    istles
    0.06
    -family
    0.06
    che
    0.06
     abroad
    0.06
    Act Density 0.029%

    No Known Activations