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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    יץ
    -0.08
     bajo
    -0.07
     técnico
    -0.07
    Ϥ
    -0.07
     egret
    -0.07
     إطار
    -0.07
     namoro
    -0.07
    LO
    -0.06
     iniciar
    -0.06
     tripod
    -0.06
    POSITIVE LOGITS
    تقييم
    0.08
    	re
    0.07
    一分钱
    0.07
    ಪ
    0.07
     Game
    0.07
    andWhere
    0.07
    $↵
    0.06
    Great
    0.06
     DAG
    0.06
    points
    0.06
    Act Density 0.020%

    No Known Activations