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

    Neuronpedia

    INDEX
    Explanations

    exponent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hugh
    -0.06
     façon
    -0.06
     FALL
    -0.06
     volunteer
    -0.06
     гла
    -0.06
    　ヽ
    -0.06
     nord
    -0.06
    dül
    -0.06
     miêu
    -0.06
     Kanye
    -0.06
    POSITIVE LOGITS
    txn
    0.07
    _tables
    0.06
    isActive
    0.06
     userinfo
    0.06
    abyrin
    0.06
     disclosures
    0.06
    	hr
    0.06
     Ab
    0.06
    kish
    0.06
    icios
    0.06
    Act Density 0.004%

    No Known Activations