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

    Neuronpedia

    INDEX
    Explanations

    parallel lines, NHS pressures, Google Search

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Coordinates
    0.66
     تک
    0.64
     Speakers
    0.64
    Koordin
    0.64
     cut
    0.64
    speakers
    0.64
     hooks
    0.61
     Considering
    0.61
     considering
    0.60
    Coordinates
    0.60
    POSITIVE LOGITS
     西
    0.84
     ages
    0.81
     midway
    0.78
    خری
    0.76
     curta
    0.75
     Dale
    0.75
     meninggal
    0.75
    धारणा
    0.71
     Gwyn
    0.71
     relais
    0.71
    Act Density 0.000%

    No Known Activations