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

    Neuronpedia

    INDEX
    Explanations

    code and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ành
    -0.08
     Lun
    -0.07
     ted
    -0.07
    Hey
    -0.06
     Beckham
    -0.06
     cables
    -0.06
    Alarm
    -0.06
     použí
    -0.06
    Get
    -0.06
     Trades
    -0.06
    POSITIVE LOGITS
     состоя
    0.07
    样子
    0.07
    appeared
    0.06
    监督
    0.06
    ../../../
    0.06
    looking
    0.06
    rch
    0.06
    ~-~-
    0.06
    (dialog
    0.06
     sağlan
    0.06
    Act Density 0.000%

    No Known Activations