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

    Neuronpedia

    INDEX
    Explanations

    subsequent attempts

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
    =sum
    -0.07
    	local
    -0.07
     Generic
    -0.07
     scenarios
    -0.07
     mature
    -0.07
    (Random
    -0.07
    uzzy
    -0.07
    显然
    -0.07
     Roo
    -0.07
    ễn
    -0.07
    POSITIVE LOGITS
    TH
    0.08
     };↵↵
    0.07
    ;
↵
↵
    0.07
    chunk
    0.07
    喉咙
    0.07
    rna
    0.07
     labelText
    0.07
    RING
    0.07
     );↵↵
    0.07
    LE
    0.06
    Act Density 0.097%

    No Known Activations