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

    Neuronpedia

    INDEX
    Explanations

    breakthrough

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sed
    -0.07
     Oxygen
    -0.07
    _pid
    -0.06
     gelişim
    -0.06
    (Person
    -0.06
    _COMP
    -0.06
     })}↵
    -0.06
    _negative
    -0.06
    	layer
    -0.06
    (icon
    -0.06
    POSITIVE LOGITS
     breakthrough
    0.15
    최고
    0.07
     sağlamak
    0.07
     Insight
    0.07
    П
    0.07
     clue
    0.06
    973
    0.06
    utut
    0.06
    974
    0.06
    ={}
    0.06
    Act Density 0.002%

    No Known Activations