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

    Neuronpedia

    INDEX
    Explanations

    algorithm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     respect
    -0.07
     یافت
    -0.07
     ปร
    -0.07
     fac
    -0.07
     Number
    -0.07
     possession
    -0.07
     gathers
    -0.06
     �
    -0.06
     Bir
    -0.06
    y
    -0.06
    POSITIVE LOGITS
     algorithm
    0.13
     Algorithm
    0.11
    Algorithm
    0.10
     algorithms
    0.10
    algorithm
    0.09
     Algorithms
    0.09
    [method
    0.08
    ธรรม
    0.07
     protocol
    0.07
    clamp
    0.07
    Act Density 0.015%

    No Known Activations