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

    Neuronpedia

    INDEX
    Explanations

    e-commerce G-Unit S-functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .•
    0.42
    .//
    0.40
    .°
    0.39
     CreateWindow
    0.39
     immersed
    0.38
     ByteBuffer
    0.38
    蓴
    0.38
     namani
    0.37
     კომპ
    0.37
    薁
    0.37
    POSITIVE LOGITS
    shaped
    0.56
    ‐
    0.56
     shaped
    0.50
    cadherin
    0.50
    type
    0.49
    commerce
    0.46
    এর
    0.45
    4
    0.44
    factor
    0.44
    N
    0.43
    Act Density 0.033%

    No Known Activations