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

    Neuronpedia

    INDEX
    Explanations

    after what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     расстояние
    0.45
    μοί
    0.44
     राजांनी
    0.43
     प्रश्न
    0.42
    ছাড়া
    0.41
    后续
    0.41
    ),\\
    0.41
    眹
    0.40
     spineItem
    0.40
     Tick
    0.39
    POSITIVE LOGITS
     komun
    0.43
     linearity
    0.41
     community
    0.40
     linear
    0.39
    inher
    0.39
     principal
    0.38
     boss
    0.38
     lots
    0.38
     producers
    0.37
    linearity
    0.37
    Act Density 0.000%

    No Known Activations