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

    Neuronpedia

    INDEX
    Explanations

    pandemic or indicates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Oceanic
    0.54
     Marble
    0.48
     Magazine
    0.46
     Laurel
    0.46
     Tg
    0.46
     Purple
    0.46
    t
    0.45
     Strength
    0.45
     Prairie
    0.44
     Liverpool
    0.44
    POSITIVE LOGITS
    où
    0.49
     países
    0.47
     nación
    0.46
     ولی
    0.44
     flew
    0.44
    უნქ
    0.44
     bribery
    0.43
     verificación
    0.43
    ów
    0.43
     ۔
    0.42
    Act Density 0.000%

    No Known Activations