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

    Neuronpedia

    INDEX
    Explanations

    what

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     لا
    -0.07
    抟
    -0.07
    ENTA
    -0.07
    倴
    -0.07
     DS
    -0.07
     always
    -0.06
    美誉
    -0.06
     defin
    -0.06
     Recursive
    -0.06
     uz
    -0.06
    POSITIVE LOGITS
    ıy
    0.08
     orderId
    0.07
    人大
    0.07
     hatch
    0.07
    酽
    0.06
    ảnh
    0.06
    もあり
    0.06
     diplomatic
    0.06
    UserId
    0.06
     Madrid
    0.06
    Act Density 0.019%

    No Known Activations