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

    Neuronpedia

    INDEX
    Explanations

    Smithsonian Magazine articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ски
    0.36
    رز
    0.35
    ീതി
    0.35
     فور
    0.34
    플
    0.34
     Spa
    0.33
     Ghe
    0.33
    mail
    0.33
     تعالى
    0.32
     gh
    0.32
    POSITIVE LOGITS
    lamiento
    0.42
     rey
    0.39
    fas
    0.39
     Rey
    0.38
    PGS
    0.38
    Rey
    0.37
     bew
    0.37
     જગ
    0.37
    entliche
    0.37
    釵
    0.37
    Act Density 0.005%

    No Known Activations