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

    Neuronpedia

    INDEX
    Explanations

    frame advance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    !!!!!!!!
    0.43
     extinguished
    0.42
     extinguish
    0.42
    ..............
    0.40
     danced
    0.39
     Herrn
    0.39
    疝
    0.39
    !!!!!!!
    0.39
    !!!!!!!!!!!!!!!!
    0.38
    Dated
    0.38
    POSITIVE LOGITS
     simulator
    0.43
    ↵↵↵
    0.38
    گاهی
    0.38
     simulating
    0.38
    ᄀ
    0.38
    वात
    0.38
    创
    0.37
     chiếm
    0.37
     Simulate
    0.37
     המס
    0.37
    Act Density 0.000%

    No Known Activations