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

    Neuronpedia

    INDEX
    Explanations

    arrangements/grids/matrices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stom
    -0.09
     air
    -0.07
    Except
    -0.07
    lių
    -0.07
    	except
    -0.07
     विविध
    -0.07
    四
    -0.07
     आज
    -0.07
     overhaul
    -0.07
     seven
    -0.07
    POSITIVE LOGITS
     beiden
    0.19
     beide
    0.16
    兩
    0.14
     halves
    0.14
     দুটি
    0.13
     두
    0.13
     দু
    0.13
    ちら
    0.13
     separately
    0.12
     bå
    0.12
    Act Density 0.084%

    No Known Activations