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

    Neuronpedia

    INDEX
    Explanations

    average metrics and trends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     conti
    0.44
     renewals
    0.40
     stav
    0.40
    炊
    0.39
    续
    0.39
    力
    0.38
    EDU
    0.37
     retailer
    0.37
     conserv
    0.36
     pair
    0.35
    POSITIVE LOGITS
     ایران
    0.49
     actuales
    0.47
     आहेत
    0.46
     हुये
    0.46
    iven
    0.45
    ljen
    0.44
     चीन
    0.44
    .¹
    0.44
    uaries
    0.44
    战争
    0.43
    Act Density 0.001%

    No Known Activations