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

    Neuronpedia

    INDEX
    Explanations

    down payment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ולוג
    0.56
    import
    0.54
     NADH
    0.54
    ار
    0.54
    I
    0.54
    स
    0.53
    То
    0.52
    س
    0.52
    は
    0.50
    Porque
    0.50
    POSITIVE LOGITS
    nés
    0.61
     paiement
    0.59
     обеспечение
    0.59
     заклю
    0.57
    наў
    0.57
    iť
    0.56
     installments
    0.55
     dá
    0.55
     ១
    0.54
    ních
    0.53
    Act Density 0.002%

    No Known Activations