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

    Neuronpedia

    INDEX
    Explanations

    silent promise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Beckman
    0.43
    ominator
    0.39
    ljanje
    0.38
    lightbox
    0.38
     setback
    0.37
    Posture
    0.36
     красивая
    0.36
    冷
    0.36
     каждым
    0.36
    levelup
    0.36
    POSITIVE LOGITS
     Cities
    0.47
     Messe
    0.41
    VIOUS
    0.40
     фра
    0.39
    uffles
    0.37
    auff
    0.37
    发布的
    0.36
     Appro
    0.36
     Drone
    0.36
     Bho
    0.36
    Act Density 0.000%

    No Known Activations