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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     HWND
    -0.06
     shoppers
    -0.06
     Cities
    -0.06
    sters
    -0.06
     doom
    -0.06
     스
    -0.06
    偷
    -0.06
     seedu
    -0.06
     Spit
    -0.06
     setzen
    -0.06
    POSITIVE LOGITS
     length
    0.06
    '],$_
    0.06
    .|
    0.06
     Length
    0.06
    ерим
    0.06
    dependency
    0.06
     @{$
    0.06
    	pr
    0.06
     violently
    0.06
     돌
    0.06
    Act Density 0.009%

    No Known Activations