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

    Neuronpedia

    INDEX
    Explanations

    Bundle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     왕
    -0.08
     legislative
    -0.07
    235
    -0.06
    ระบ
    -0.06
    帝
    -0.06
     commanded
    -0.06
    gov
    -0.06
    quit
    -0.06
     Gov
    -0.06
    Japgolly
    -0.06
    POSITIVE LOGITS
    فات
    0.07
    握
    0.07
     khá
    0.07
     �
    0.07
     piled
    0.06
     Parallel
    0.06
     �
    0.06
    blogs
    0.06
     Keywords
    0.06
    (batch
    0.06
    Act Density 0.003%

    No Known Activations