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

    Neuronpedia

    INDEX
    Explanations

    place names, cities, states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tt
    0.57
     C
    0.57
     is
    0.56
    k
    0.53
    ક
    0.52
     SHOP
    0.50
     R
    0.50
    ח
    0.49
     intersects
    0.48
     С
    0.47
    POSITIVE LOGITS
    ချက်
    0.58
    ailles
    0.50
    royo
    0.49
    verson
    0.49
    abhavam
    0.49
    போதும்
    0.48
    quisitos
    0.48
    สำหรับการ
    0.48
     လုပ်
    0.46
    <unused645>
    0.46
    Act Density 0.021%

    No Known Activations