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

    Neuronpedia

    INDEX
    Explanations

    context and container

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     спо
    0.64
    ené
    0.62
     записи
    0.59
     схемы
    0.58
     обра
    0.56
     בו
    0.54
     Đó
    0.54
     đó
    0.54
    رويج
    0.54
     ча
    0.53
    POSITIVE LOGITS
    OS
    0.63
    ع
    0.62
    Music
    0.61
     Fundamental
    0.61
    OM
    0.60
    MS
    0.60
     Music
    0.58
    M
    0.56
    ༨
    0.56
    UN
    0.55
    Act Density 0.001%

    No Known Activations