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

    Neuronpedia

    INDEX
    Explanations

    Math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     Peg
    -0.06
    (↵
    -0.06
    _b
    -0.06
    ],↵↵
    -0.06
    Reusable
    -0.06
     {}).
    -0.06
    Linear
    -0.06
     choking
    -0.06
    _Abstract
    -0.06
    POSITIVE LOGITS
    .problem
    0.07
     Kiev
    0.06
    .small
    0.06
    xmin
    0.06
     lasted
    0.06
    .Reporting
    0.06
     cualquier
    0.06
    ými
    0.06
     Deadline
    0.06
     refugee
    0.06
    Act Density 0.005%

    No Known Activations