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

    Neuronpedia

    INDEX
    Explanations

    arithmetic addition and assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ucked
    0.54
    âtre
    0.51
    ne
    0.48
    ry
    0.46
    nese
    0.46
    raž
    0.45
    uyên
    0.45
    rift
    0.44
    irim
    0.44
    REET
    0.44
    POSITIVE LOGITS
     ulteriori
    0.46
     "\
    0.45
    委員
    0.43
    与
    0.43
    前
    0.41
    力和
    0.40
     polygon
    0.40
    面前
    0.40
    也要
    0.40
     tovább
    0.39
    Act Density 0.029%

    No Known Activations