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

    Neuronpedia

    INDEX
    Explanations

    Daniel

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inventions
    -0.07
    	except
    -0.06
     ipAddress
    -0.06
     rằng
    -0.06
    _Load
    -0.06
    _loading
    -0.06
    (Language
    -0.06
     như
    -0.06
    کری
    -0.06
    城市
    -0.06
    POSITIVE LOGITS
    ,mid
    0.07
     sach
    0.06
     tok
    0.06
    adoo
    0.06
    เคล
    0.06
     Side
    0.06
    _CAPTURE
    0.06
    <>↵
    0.06
    Side
    0.06
     fflush
    0.06
    Act Density 0.036%

    No Known Activations