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

    Neuronpedia

    INDEX
    Explanations

    Showing genuine interest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ريقيا
    0.46
    ։
    0.42
    эй
    0.40
     aprile
    0.39
    pyridazin
    0.39
     elucidated
    0.39
     आरमारा
    0.39
    >\
    0.39
    neas
    0.39
     beras
    0.38
    POSITIVE LOGITS
     Wiss
    0.45
     survival
    0.38
     workshops
    0.38
     radioactivity
    0.37
     szt
    0.36
     genetics
    0.35
     jumbo
    0.35
    によっては
    0.35
    تس
    0.35
    exception
    0.35
    Act Density 0.001%

    No Known Activations