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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inaccessible
    -0.07
     unconventional
    -0.06
     Lebens
    -0.06
     inconsistent
    -0.06
     Nha
    -0.06
    оюз
    -0.06
    오는
    -0.06
    eresa
    -0.06
     Lê
    -0.06
     detrimental
    -0.06
    POSITIVE LOGITS
     pytest
    0.06
     Mighty
    0.06
    ائب
    0.06
    	None
    0.06
    (src
    0.06
    thank
    0.06
    _distribution
    0.06
     unable
    0.06
    Κ
    0.06
     AMAZ
    0.06
    Act Density 0.223%

    No Known Activations