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

    Neuronpedia

    INDEX
    Explanations

    language focus and play

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.78
    mujer
    0.78
    itió
    0.73
    muş
    0.71
    u
    0.70
    lá
    0.69
    lamps
    0.68
    med
    0.66
    سي
    0.66
    يا
    0.66
    POSITIVE LOGITS
    ור
    1.01
     Language
    0.96
     Languages
    0.86
     language
    0.84
    Language
    0.80
    ות
    0.77
     Describes
    0.77
    ور
    0.77
    ี
    0.76
    ิ
    0.73
    Act Density 0.073%

    No Known Activations