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

    Neuronpedia

    INDEX
    Explanations

    news stories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ickness
    -0.07
    块
    -0.06
     probe
    -0.06
    ymce
    -0.06
    -red
    -0.06
    惡
    -0.06
     пед
    -0.06
     subject
    -0.06
     du
    -0.06
    itate
    -0.06
    POSITIVE LOGITS
    大湾区
    0.08
    ephir
    0.07
    atoi
    0.07
    Enum
    0.07
    时空
    0.07
    grpc
    0.07
    ℍ
    0.06
     нельз
    0.06
    ﺑ
    0.06
     NotSupportedException
    0.06
    Act Density 0.102%

    No Known Activations