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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (curr
    -0.06
     prefers
    -0.06
     diversas
    -0.06
     tert
    -0.06
    rez
    -0.06
     flap
    -0.06
     traumatic
    -0.06
     nutrit
    -0.06
     swingerclub
    -0.06
     chlor
    -0.06
    POSITIVE LOGITS
    .getAttribute
    0.07
     repeated
    0.07
     görmek
    0.06
    .neo
    0.06
     Çünkü
    0.06
     saint
    0.06
    伊
    0.06
    -value
    0.06
    	success
    0.06
    Thông
    0.06
    Act Density 0.000%

    No Known Activations