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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kům
    -0.07
    _KERNEL
    -0.07
     dbl
    -0.07
    セ
    -0.07
    以来
    -0.07
     лист
    -0.06
    RefCount
    -0.06
    /OR
    -0.06
    医院
    -0.06
    [char
    -0.06
    POSITIVE LOGITS
     doub
    0.07
     Stops
    0.07
    піон
    0.07
     grund
    0.06
     probability
    0.06
     collaps
    0.06
     initiate
    0.06
    ates
    0.06
     hạng
    0.06
    lates
    0.06
    Act Density 0.010%

    No Known Activations