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

    Neuronpedia

    INDEX
    Explanations

    navigate to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ใช
    0.77
    扱う
    0.72
    止
    0.67
     использу
    0.67
     بیاکت
    0.66
     придума
    0.65
     houden
    0.65
    octet
    0.65
    保有
    0.64
    扱
    0.64
    POSITIVE LOGITS
     visits
    2.28
     visit
    2.25
     travels
    2.16
    前往
    2.15
     journey
    2.14
     Visits
    2.11
     travel
    2.08
     pergi
    2.07
     traveled
    2.05
     traveling
    2.02
    Act Density 1.517%

    No Known Activations