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

    Neuronpedia

    INDEX
    Explanations

    profit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    339
    -0.07
    speaker
    -0.06
    354
    -0.06
    134
    -0.06
    る
    -0.06
     cyc
    -0.06
    ไล
    -0.06
    932
    -0.06
    ials
    -0.06
    319
    -0.06
    POSITIVE LOGITS
     unintention
    0.07
    .Alignment
    0.06
    etros
    0.06
    ocumented
    0.06
    ุตสาห
    0.06
    [H
    0.06
     Hilton
    0.06
     Tehran
    0.06
    Interested
    0.06
    (QtGui
    0.06
    Act Density 0.001%

    No Known Activations