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

    Neuronpedia

    INDEX
    Explanations

    romantic attraction, tolerance classes, handler mapping, angle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hur
    0.50
     Blue
    0.48
     Heritage
    0.47
     red
    0.46
     plate
    0.46
     totem
    0.46
     portfolios
    0.45
     stress
    0.44
    ول
    0.44
     portfolio
    0.44
    POSITIVE LOGITS
    slidesPerGroup
    0.49
    𝚔
    0.49
     ಅಪ
    0.49
     recomendaciones
    0.48
    berat
    0.48
     diğer
    0.47
     excelentes
    0.47
     singleRun
    0.47
    فیر
    0.47
    bedingungen
    0.47
    Act Density 0.000%

    No Known Activations