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

    Neuronpedia

    INDEX
    Explanations

    Gartner

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CLASS
    -0.07
     Elvis
    -0.06
     updated
    -0.06
     Germany
    -0.06
     resign
    -0.06
     سل
    -0.06
     fier
    -0.06
    ihar
    -0.06
     criticism
    -0.06
     corrupt
    -0.06
    POSITIVE LOGITS
    .opts
    0.07
     CultureInfo
    0.07
     junk
    0.06
    .sqrt
    0.06
    [:]
    0.06
    .details
    0.06
     заболевания
    0.06
     polarization
    0.06
    (uri
    0.06
    _question
    0.06
    Act Density 0.001%

    No Known Activations