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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oj
    -0.07
     cucumber
    -0.07
     Funds
    -0.07
    418
    -0.07
     ducks
    -0.07
    سن
    -0.06
    osh
    -0.06
     incentive
    -0.06
     دخ
    -0.06
    947
    -0.06
    POSITIVE LOGITS
    НО
    0.07
    _CONSOLE
    0.06
    	un
    0.06
     применя
    0.06
     capitalist
    0.06
    ๊
    0.06
    (vp
    0.06
     inne
    0.06
     všichni
    0.06
    warz
    0.06
    Act Density 0.111%

    No Known Activations