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

    Neuronpedia

    INDEX
    Explanations

    exciting quests, accurate tracking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    في
    0.57
    بي
    0.55
    би
    0.52
    но
    0.51
    И
    0.47
    ин
    0.47
    0
    0.47
    حي
    0.46
    лки
    0.46
    Би
    0.46
    POSITIVE LOGITS
     Operations
    0.48
    ata
    0.48
     elles
    0.47
    asana
    0.47
    urization
    0.46
    usage
    0.46
    तपुर
    0.46
     supply
    0.46
     ð
    0.44
    aney
    0.44
    Act Density 0.000%

    No Known Activations