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

    Neuronpedia

    INDEX
    Explanations

    Information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     South
    -0.07
    _ENABLED
    -0.07
    .error
    -0.07
     DIG
    -0.07
    ByUsername
    -0.07
     Teaching
    -0.06
     Suz
    -0.06
     UNIVERS
    -0.06
     handleError
    -0.06
    拊
    -0.06
    POSITIVE LOGITS
     linen
    0.06
    农家乐
    0.06
    сло
    0.06
    裂缝
    0.06
     exploding
    0.06
    四季
    0.06
     centerpiece
    0.06
    瑢
    0.06
    笑了笑
    0.06
     packing
    0.06
    Act Density 0.001%

    No Known Activations