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

    Neuronpedia

    INDEX
    Explanations

    run directly; script

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     temporary
    0.70
     UEFA
    0.70
    ppermint
    0.69
    おすすめです
    0.68
     activity
    0.68
     memory
    0.68
     trips
    0.66
     tri
    0.65
     recomend
    0.65
     temporarily
    0.65
    POSITIVE LOGITS
     نباش
    0.94
     هستند
    0.82
     individuales
    0.82
    ндарт
    0.80
    窈
    0.80
    인데
    0.79
     باشند
    0.79
     nhàng
    0.79
     वर्तमान
    0.78
     നേരി
    0.78
    Act Density 0.034%

    No Known Activations