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

    Neuronpedia

    INDEX
    Explanations

    literacy and reading skills for children

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    엣
    0.42
    রস
    0.42
     философ
    0.40
    PayPal
    0.39
     (++
    0.38
    隈
    0.38
     pelanggan
    0.38
     skór
    0.38
    ション
    0.37
    ϑ
    0.37
    POSITIVE LOGITS
     literacy
    1.68
     Literacy
    1.55
     reading
    1.52
     Reading
    1.34
    Reading
    1.27
     literate
    1.26
     READING
    1.24
    reading
    1.23
     읽
    1.19
     lettura
    1.19
    Act Density 0.020%

    No Known Activations