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

    Neuronpedia

    INDEX
    Explanations

    software

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     attractions
    -0.07
     Ridge
    -0.07
     Term
    -0.07
     cyn
    -0.07
    ét
    -0.07
    *k
    -0.07
     neuron
    -0.07
    -circle
    -0.06
     picks
    -0.06
     York
    -0.06
    POSITIVE LOGITS
    software
    0.10
     Software
    0.10
     software
    0.09
    Software
    0.08
     SOFTWARE
    0.08
     그래
    0.08
    sov
    0.07
     Sophie
    0.07
     slideshow
    0.07
    SOFTWARE
    0.07
    Act Density 0.031%

    No Known Activations