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

    Neuronpedia

    INDEX
    Explanations

    closing parenthesis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pornost
    -0.07
     ámbito
    -0.07
    תחוש
    -0.07
    acin
    -0.07
     노력
    -0.07
    ٹ
    -0.07
    fullName
    -0.07
    珙
    -0.07
     información
    -0.07
    接受采访
    -0.06
    POSITIVE LOGITS
     readonly
    0.09
     отлично
    0.07
    뎁
    0.07
    连
    0.07
     meals
    0.07
     RETURN
    0.07
    主机
    0.07
     replen
    0.07
     LOCK
    0.07
     obr
    0.07
    Act Density 0.013%

    No Known Activations