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

    Neuronpedia

    INDEX
    Explanations

    mathematical sequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     muscle
    -0.08
     protr
    -0.08
     excavation
    -0.08
     embroidery
    -0.07
     militar
    -0.07
     military
    -0.07
     Archae
    -0.07
    Fence
    -0.07
     स्थल
    -0.07
    Award
    -0.07
    POSITIVE LOGITS
     Recipro
    0.14
     reciprocal
    0.14
     reciproc
    0.13
     Ratio
    0.11
     cyclic
    0.11
    _inverse
    0.11
     Rat
    0.10
     ratios
    0.10
     invers
    0.10
     Cycle
    0.10
    Act Density 0.034%

    No Known Activations