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

    Neuronpedia

    INDEX
    Explanations

    atmosphere and mood

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ዷ
    0.29
     edibles
    0.27
     menjalankan
    0.27
     ಯಾವುದೇ
    0.27
    Pokud
    0.26
     모든
    0.26
     파일을
    0.26
     bruke
    0.26
    Maxima
    0.26
     outputs
    0.26
    POSITIVE LOGITS
     melancholy
    0.45
     nostalgia
    0.42
     innocence
    0.41
     arrogance
    0.41
     defiance
    0.40
     awe
    0.40
     humility
    0.39
     grandeur
    0.39
     mysticism
    0.38
     individuality
    0.38
    Act Density 0.745%

    No Known Activations