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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    irror
    -0.06
     Guardians
    -0.06
     CHAR
    -0.06
     showcasing
    -0.06
     predators
    -0.06
     Swap
    -0.06
    及び
    -0.06
    origin
    -0.06
    tabs
    -0.06
     Yad
    -0.06
    POSITIVE LOGITS
    HK
    0.08
     errone
    0.07
    	ASSERT
    0.07
    	dist
    0.06
     탈
    0.06
    жно
    0.06
    .digest
    0.06
     tr
    0.06
    .stub
    0.06
     balcon
    0.06
    Act Density 0.000%

    No Known Activations