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

    Neuronpedia

    INDEX
    Explanations

    art, games, food descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     other
    1.06
     ilang
    1.00
    paces
    0.98
    پلز
    0.95
    ⓪
    0.95
     Осо
    0.94
    ome
    0.93
     sonra
    0.93
     Este
    0.92
    hee
    0.91
    POSITIVE LOGITS
    isierte
    0.92
    iskt
    0.88
    শিপ
    0.88
     roomy
    0.87
    श
    0.87
    жный
    0.87
     Dorchester
    0.87
    ροφο
    0.86
    uated
    0.86
    isasi
    0.86
    Act Density 0.052%

    No Known Activations