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

    Neuronpedia

    INDEX
    Explanations

    build trust, contact Earth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     backup
    0.77
     आधे
    0.75
     खुलने
    0.70
    Backup
    0.70
    Product
    0.69
    的
    0.65
     Backup
    0.63
    Larg
    0.62
    Or
    0.62
    Category
    0.61
    POSITIVE LOGITS
     zorunda
    0.88
    欴
    0.84
     entusi
    0.83
    ává
    0.83
    ody
    0.83
     ț
    0.83
     カメラ
    0.82
    attuale
    0.81
    ování
    0.80
    燡
    0.79
    Act Density 0.000%

    No Known Activations