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

    Neuronpedia

    INDEX
    Explanations

    math notation and directions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ights
    0.52
    👜
    0.47
    侶
    0.47
    洶
    0.47
    iour
    0.46
    തിനാ
    0.46
     commencent
    0.46
    rews
    0.46
     दिन
    0.46
    այ
    0.45
    POSITIVE LOGITS
    Plate
    0.49
    an
    0.45
    Marketing
    0.45
    0
    0.45
    Birmingham
    0.45
     آ
    0.45
    Block
    0.44
    u
    0.44
    Design
    0.44
    corner
    0.44
    Act Density 0.002%

    No Known Activations