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

    Neuronpedia

    INDEX
    Explanations

    lucky numbers and charts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    piar
    0.40
    Orbit
    0.37
    ucs
    0.37
    ut
    0.36
     #'
    0.36
     thay
    0.36
    star
    0.35
    grid
    0.35
    Binary
    0.35
    \_
    0.35
    POSITIVE LOGITS
    ગર
    0.36
     outstretched
    0.35
    configFile
    0.34
     lago
    0.33
    THEOREM
    0.32
     gamanam
    0.32
     fratello
    0.31
    .”[
    0.31
    旁邊
    0.31
     attham
    0.31
    Act Density 0.000%

    No Known Activations