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

    Neuronpedia

    INDEX
    Explanations

    x y coordinates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     және
    0.70
     Sonja
    0.64
    하면서
    0.63
     ruim
    0.62
     먼저
    0.62
     Lombok
    0.62
    하며
    0.61
     sekaligus
    0.61
     Chengdu
    0.60
     Dordrecht
    0.59
    POSITIVE LOGITS
     cooper
    0.64
     CON
    0.62
    itats
    0.59
    wość
    0.59
    ורי
    0.58
    orkan
    0.57
     कर्फ्यू
    0.56
    '_
    0.55
     خان
    0.55
    草
    0.55
    Act Density 0.015%

    No Known Activations