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

    Neuronpedia

    INDEX
    Explanations

    "predict"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    甓
    -0.07
     authService
    -0.07
    öffent
    -0.07
     SSR
    -0.07
     drill
    -0.07
    跶
    -0.07
    �
    -0.07
     rozpoc
    -0.07
    这么多
    -0.07
    인터넷
    -0.07
    POSITIVE LOGITS
     predictions
    0.08
     \
    0.07
     predicted
    0.07
    -le
    0.07
    生產
    0.07
     Ped
    0.06
    ,
    0.06
     CAD
    0.06
     expanding
    0.06
     flat
    0.06
    Act Density 0.035%

    No Known Activations