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

    Neuronpedia

    INDEX
    Explanations

    payment in installments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ב
    0.84
    ية
    0.82
    ک
    0.76
    ה
    0.76
    ة
    0.73
    ты
    0.71
    не
    0.70
     and
    0.68
    ı
    0.68
    cı
    0.66
    POSITIVE LOGITS
     installments
    0.76
     installment
    0.63
     dhinak
    0.62
     nových
    0.60
     instalment
    0.58
     буду
    0.57
     graus
    0.56
     instalments
    0.56
     ônibus
    0.56
     دست
    0.55
    Act Density 0.001%

    No Known Activations