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

    Neuronpedia

    INDEX
    Explanations

    disabilities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     japanese
    -0.07
     government
    -0.07
     approves
    -0.06
     lone
    -0.06
    Canada
    -0.06
    normally
    -0.06
    antine
    -0.06
     âm
    -0.06
     freedom
    -0.06
     Jenkins
    -0.06
    POSITIVE LOGITS
    卟
    0.08
    텣
    0.07
    맙
    0.07
     Бо
    0.07
    PATCH
    0.07
    猁
    0.07
    quisar
    0.07
    Name
    0.07
     müş
    0.07
     concat
    0.07
    Act Density 0.095%

    No Known Activations