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

    Neuronpedia

    INDEX
    Explanations

    a step further

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.74
     তাহলে
    0.59
    models
    0.54
     Bücher
    0.54
    ysty
    0.53
     aika
    0.53
    的部分
    0.52
    Waves
    0.52
     forskjellige
    0.52
    land
    0.50
    POSITIVE LOGITS
    ка
    0.77
     curtailed
    0.72
     streamlined
    0.65
     discredited
    0.64
     corrobor
    0.64
     watertight
    0.64
     documented
    0.63
    ل
    0.63
     pared
    0.63
    री
    0.62
    Act Density 0.001%

    No Known Activations