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

    Neuronpedia

    INDEX
    Explanations

    Code/URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )↵↵↵↵↵↵
    -0.07
    $row
    -0.07
     theres
    -0.06
    eč
    -0.06
    .↵↵↵↵↵↵
    -0.06
    _proc
    -0.06
     BeautifulSoup
    -0.06
     womens
    -0.06
    也有
    -0.06
     de
    -0.06
    POSITIVE LOGITS
    Daily
    0.06
    本当
    0.06
     trưởng
    0.06
    τωση
    0.06
     unwind
    0.06
    rupt
    0.06
     Types
    0.06
    	JOptionPane
    0.06
    ONG
    0.06
    akra
    0.06
    Act Density 0.008%

    No Known Activations