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

    Neuronpedia

    INDEX
    Explanations

    common generic text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Check
    -0.07
     Stre
    -0.07
    024
    -0.07
    وین
    -0.07
     *.
    -0.06
    	act
    -0.06
    MEM
    -0.06
     अपर
    -0.06
     unfortunate
    -0.06
     元
    -0.06
    POSITIVE LOGITS
     місто
    0.06
    />↵↵
    0.06
    abcdefghijklmnop
    0.06
    进一步
    0.06
    <style
    0.06
     Recall
    0.06
    Physics
    0.06
     الرسمي
    0.06
     africa
    0.06
    Logout
    0.06
    Act Density 0.100%

    No Known Activations