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

    Neuronpedia

    INDEX
    Explanations

    latex commands and settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     verde
    0.39
     arXiv
    0.38
     perturbative
    0.38
     spectroscopic
    0.36
     تړ
    0.36
     pedagogical
    0.35
     Mathematica
    0.35
     institucional
    0.33
     sprawie
    0.33
     Faculdade
    0.33
    POSITIVE LOGITS
    emps
    0.33
     overr
    0.33
    depth
    0.33
     flush
    0.32
    ivity
    0.32
     series
    0.32
    oré
    0.32
    رفة
    0.31
    overlaps
    0.31
    Registers
    0.31
    Act Density 0.000%

    No Known Activations