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

    Neuronpedia

    INDEX
    Explanations

    AR, Augmented Reality, XR

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    द्रोह
    0.45
     Burundi
    0.42
     gerais
    0.42
     Ferreira
    0.42
     freno
    0.40
     Blogging
    0.39
     flanks
    0.39
     fenn
    0.38
    鯽
    0.38
     Brah
    0.38
    POSITIVE LOGITS
     AR
    1.11
     Augmented
    1.02
    AR
    1.00
     augmented
    0.95
    augmented
    0.89
     XR
    0.84
    Reality
    0.82
    XR
    0.78
     Reality
    0.77
    Aug
    0.75
    Act Density 0.026%

    No Known Activations