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
     Win
    -0.07
     BUFF
    -0.07
     competence
    -0.07
     ผม
    -0.07
     various
    -0.06
     reputed
    -0.06
    功能性
    -0.06
     prime
    -0.06
     showed
    -0.06
     함
    -0.06
    POSITIVE LOGITS
    领导人
    0.08
    죽
    0.07
    抬头
    0.07
    Overlay
    0.07
    奢华
    0.07
     lasers
    0.07
    oh
    0.07
    建筑业
    0.07
     עוסק
    0.07
    ika
    0.07
    Act Density 0.124%

    No Known Activations