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

    Neuronpedia

    INDEX
    Explanations

    me

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ");↵
    -0.07
     projections
    -0.07
    /exp
    -0.07
     financ
    -0.06
    istani
    -0.06
    PROCESS
    -0.06
    281
    -0.06
    idata
    -0.06
     dna
    -0.06
    (dom
    -0.06
    POSITIVE LOGITS
    е
    0.07
     ředitel
    0.07
     hàng
    0.06
     estado
    0.06
    toDouble
    0.06
    _enqueue
    0.06
    stantiateViewController
    0.06
    .dumps
    0.06
    Essay
    0.06
     Hồ
    0.06
    Act Density 0.231%

    No Known Activations