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

    Neuronpedia

    INDEX
    Explanations

    there

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (parameters
    -0.06
     currently
    -0.06
    ，存于
    -0.06
    fair
    -0.06
    "path
    -0.06
     a
    -0.06
     k
    -0.06
    ))),
    -0.06
    佳
    -0.06
    ")),
    -0.06
    POSITIVE LOGITS
     dbname
    0.07
     thuốc
    0.07
     Multi
    0.07
    rops
    0.06
     periodo
    0.06
    主義
    0.06
     за
    0.06
    érie
    0.06
    .Number
    0.06
    entity
    0.06
    Act Density 0.001%

    No Known Activations