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

    Neuronpedia

    INDEX
    Explanations

    Winning cups in competitions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wire
    -0.07
    how
    -0.07
     ceremonies
    -0.07
    pictures
    -0.07
     Austria
    -0.06
     SEX
    -0.06
     weekends
    -0.06
     Dance
    -0.06
     story
    -0.06
    (expression
    -0.06
    POSITIVE LOGITS
    Pooling
    0.06
    pell
    0.06
    ερό
    0.06
    ption
    0.06
                    
    0.06
    _variation
    0.06
    eventId
    0.06
     LOG
    0.06
     अज
    0.06
    ΟΔ
    0.06
    Act Density 0.019%

    No Known Activations