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

    Neuronpedia

    INDEX
    Explanations

    code, revenue, french law

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    FAB
    -0.07
    ercise
    -0.07
    Module
    -0.07
    module
    -0.07
    fis
    -0.07
     Jaz
    -0.07
     module
    -0.07
    Poker
    -0.07
    Static
    -0.07
     geological
    -0.07
    POSITIVE LOGITS
     aml
    0.09
     uncanny
    0.09
     EACH
    0.08
    	except
    0.08
     élu
    0.08
    áne
    0.08
     Blond
    0.08
    叫什么
    0.08
    ancers
    0.08
     surprising
    0.08
    Act Density 0.000%

    No Known Activations