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

    Neuronpedia

    INDEX
    Explanations

    confidential information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مت
    0.44
    ʇ
    0.44
    decimal
    0.43
    otte
    0.43
    வனி
    0.43
    Ꭾ
    0.43
    cimientos
    0.42
    fileExists
    0.42
    flix
    0.42
    يار
    0.42
    POSITIVE LOGITS
    々な
    0.50
     INDEX
    0.49
     arriba
    0.45
     coalition
    0.44
     MATH
    0.44
     solstice
    0.44
    ท่องเที่ยว
    0.44
    ुप
    0.44
     गईं
    0.43
     AGEN
    0.43
    Act Density 0.000%

    No Known Activations