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

    Neuronpedia

    INDEX
    Explanations

    LaTeX package inclusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     transcriptional
    0.75
     achievable
    0.69
     structured
    0.67
     grained
    0.66
     osmotic
    0.66
     Capac
    0.65
     transplantation
    0.65
     staged
    0.64
     recreational
    0.64
     attainable
    0.64
    POSITIVE LOGITS
    [
    1.04
    {
    1.03
    [%
    0.96
    []{
    0.91
    klady
    0.85
    [-
    0.79
    [\
    0.79
    elekt
    0.75
    FileUpload
    0.75
    %、
    0.74
    Act Density 0.001%

    No Known Activations