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

    Neuronpedia

    INDEX
    Explanations

    Groups and hierarchies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Points
    -0.07
    _dark
    -0.07
     Better
    -0.06
     Hakk
    -0.06
    806
    -0.06
    Positive
    -0.06
     Adult
    -0.06
     Tested
    -0.06
     Generating
    -0.06
    ilk
    -0.06
    POSITIVE LOGITS
     relates
    0.06
    βολή
    0.06
     крас
    0.06
    quant
    0.06
    ，现在
    0.06
     найкра
    0.06
    于
    0.06
     української
    0.06
    .Min
    0.06
     Crusher
    0.06
    Act Density 0.109%

    No Known Activations