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

    Neuronpedia

    INDEX
    Explanations

    want to know/read

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    кратно
    0.84
    Nasdaq
    0.81
    ngthen
    0.80
    routingHeader
    0.80
    Metall
    0.80
     گوئی
    0.79
     కీలక
    0.78
    ्युनिकेशन
    0.77
     Flooring
    0.77
    zerw
    0.77
    POSITIVE LOGITS
    하는
    1.04
    ers
    1.04
    者を
    1.01
    者の
    0.98
    者に
    0.95
    ingen
    0.93
    atori
    0.92
    ingin
    0.90
    یدن
    0.90
    者的
    0.90
    Act Density 0.120%

    No Known Activations