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

    Neuronpedia

    INDEX
    Explanations

    sustainability and efficiency

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UMA
    0.74
     woorden
    0.74
    uma
    0.73
    cena
    0.70
    changers
    0.69
     Один
    0.68
    therm
    0.66
    达成
    0.66
     propria
    0.66
     perifer
    0.65
    POSITIVE LOGITS
     विभ
    0.72
     Polarization
    0.71
     Butch
    0.68
     Erosion
    0.67
     Coroner
    0.67
     Taxonomic
    0.66
    麵
    0.66
     Sentencing
    0.65
     Police
    0.65
     الجسم
    0.65
    Act Density 0.002%

    No Known Activations