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

    Neuronpedia

    INDEX
    Explanations

    lean together

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    餃
    0.40
     Kog
    0.39
    缮
    0.39
     พร้อม
    0.38
    ॉक
    0.38
    笘
    0.37
    粝
    0.37
     Circus
    0.37
     commandBuffer
    0.37
    ለያዩ
    0.37
    POSITIVE LOGITS
    Height
    0.42
    intention
    0.42
    an
    0.41
     originally
    0.41
    ans
    0.41
    Greater
    0.40
    ан
    0.40
    ">=</
    0.39
    anst
    0.39
    hecy
    0.38
    Act Density 0.000%

    No Known Activations