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

    Neuronpedia

    INDEX
    Explanations

    creating illusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BEAUT
    0.60
     Beauty
    0.52
     beauty
    0.51
    beauty
    0.49
     beautiful
    0.48
     Beautiful
    0.47
     beleza
    0.46
     Schönheit
    0.46
    Beauty
    0.45
     beauties
    0.45
    POSITIVE LOGITS
     illusion
    1.20
     Illusion
    1.03
    illusion
    1.00
     illusions
    0.99
     illusory
    0.94
     ilusión
    0.89
     visually
    0.88
    視覺
    0.88
     perceived
    0.86
     aparent
    0.85
    Act Density 0.068%

    No Known Activations