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

    Neuronpedia

    INDEX
    Explanations

    ways to get around

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    wy
    0.44
     bevorzug
    0.40
    íd
    0.39
    tipped
    0.39
    允許
    0.38
     felony
    0.38
     concierto
    0.38
     virkelig
    0.38
    wd
    0.37
     polémica
    0.37
    POSITIVE LOGITS
    Https
    0.41
     www
    0.40
     Through
    0.40
     kiosks
    0.40
     Image
    0.40
    amers
    0.39
     Sounds
    0.39
    Sounds
    0.38
     Scenes
    0.38
     वाहत
    0.38
    Act Density 0.002%

    No Known Activations