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

    Neuronpedia

    INDEX
    Explanations

    can be, while doing, need

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     North
    0.67
    )
    0.59
     for
    0.54
     from
    0.52
    North
    0.52
     with
    0.50
    );
    0.50
     Languages
    0.50
     World
    0.48
     the
    0.47
    POSITIVE LOGITS
     ngunit
    0.57
     bottlene
    0.51
     proteína
    0.48
    pSensor
    0.48
     indietro
    0.47
    挕
    0.46
     mógł
    0.46
     alcoved
    0.46
     adduct
    0.46
     carène
    0.46
    Act Density 0.000%

    No Known Activations