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

    Neuronpedia

    INDEX
    Explanations

    code and data handling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Remark
    -0.07
     moins
    -0.06
     thú
    -0.06
     pb
    -0.06
    semble
    -0.06
    _aw
    -0.06
    ETHER
    -0.06
    lists
    -0.06
     combin
    -0.06
    leyen
    -0.06
    POSITIVE LOGITS
     pedestrian
    0.07
    850
    0.06
     จำก
    0.06
     supra
    0.06
     objections
    0.06
    홈
    0.06
    出
    0.06
    classNames
    0.06
    858
    0.06
    PreparedStatement
    0.06
    Act Density 0.138%

    No Known Activations