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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     airstrikes
    -0.07
    RowCount
    -0.07
    >)
    -0.06
    	Point
    -0.06
     sper
    -0.06
    879
    -0.06
     голод
    -0.06
    [int
    -0.06
    -football
    -0.06
     Mutable
    -0.06
    POSITIVE LOGITS
     şark
    0.06
    μιο
    0.06
    FILES
    0.06
    (SE
    0.06
    �
    0.06
     дет
    0.06
     legislators
    0.06
    anical
    0.06
    ErrMsg
    0.06
     rst
    0.06
    Act Density 0.009%

    No Known Activations