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

    Neuronpedia

    INDEX
    Explanations

    programming, data, lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     throughput
    0.40
     inscrição
    0.39
     holders
    0.38
     badge
    0.38
    ല്ലാതെ
    0.38
    持って
    0.37
    Py
    0.37
    rectangle
    0.37
    label
    0.36
    badge
    0.36
    POSITIVE LOGITS
    ScienceStudent
    0.39
     Aux
    0.39
     आयुक्त
    0.38
    aksi
    0.38
    应
    0.38
     Transplant
    0.36
    jl
    0.36
     ዋና
    0.36
     AliExpress
    0.36
     Fakult
    0.35
    Act Density 0.006%

    No Known Activations