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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Convert
    -0.07
     HttpContext
    -0.07
    �
    -0.07
     Katherine
    -0.07
     Printer
    -0.07
    '^
    -0.07
     raging
    -0.07
    Begin
    -0.07
    歅
    -0.06
     biopsy
    -0.06
    POSITIVE LOGITS
    一般来说
    0.07
    guided
    0.06
    民主
    0.06
    双重
    0.06
    /sub
    0.06
     dominance
    0.06
     pero
    0.06
    磁
    0.06
    [Unit
    0.06
     Wi
    0.06
    Act Density 0.231%

    No Known Activations