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

    Neuronpedia

    INDEX
    Explanations

    Abs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     discipline
    -0.08
     beginning
    -0.07
    `↵
    -0.06
    误
    -0.06
    ’.
    -0.06
    Cols
    -0.06
    izon
    -0.06
    .getSeconds
    -0.06
    -band
    -0.06
     …↵↵
    -0.06
    POSITIVE LOGITS
     reliant
    0.08
    .ArgumentParser
    0.07
     Omn
    0.07
    ослав
    0.06
     Ottawa
    0.06
     ост
    0.06
     Norwich
    0.06
     FUNCTIONS
    0.06
     Orth
    0.06
    ubernetes
    0.06
    Act Density 0.209%

    No Known Activations