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

    Neuronpedia

    INDEX
    Explanations

    from source

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Atlet
    1.02
     taping
    0.95
     τε
    0.92
     ومع
    0.90
     Matic
    0.89
     odor
    0.88
     Airways
    0.88
     angolo
    0.87
     bouts
    0.87
     tarif
    0.86
    POSITIVE LOGITS
    نا
    0.96
    ों
    0.96
    ast
    0.96
    ship
    0.95
    ित
    0.90
    ्स
    0.88
    scene
    0.88
    ној
    0.85
    Terminology
    0.85
    ’
    0.84
    Act Density 0.000%

    No Known Activations