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

    Neuronpedia

    INDEX
    Explanations

    annual growth rate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nir
    0.37
    نے
    0.36
    Mex
    0.36
    omorphisms
    0.36
    Multipart
    0.36
    They
    0.35
    ductory
    0.35
    Our
    0.35
    Complex
    0.34
    We
    0.34
    POSITIVE LOGITS
     averaging
    0.44
     yum
    0.44
     annually
    0.41
    每年
    0.41
     averages
    0.40
     averaged
    0.40
     wets
    0.40
    以便
    0.40
     કારણ
    0.39
     civiles
    0.39
    Act Density 0.001%

    No Known Activations