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

    Neuronpedia

    INDEX
    Explanations

    foreign language words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     и
    0.47
     दक्षता
    0.44
     збере
    0.42
    既に
    0.42
    殄
    0.41
    すべての
    0.41
    дения
    0.40
     pursuant
    0.39
     ಎಲ್ಲಾ
    0.38
     благодаря
    0.38
    POSITIVE LOGITS
     inoltre
    0.46
    بعض
    0.46
     alguns
    0.44
     políticos
    0.44
     könnte
    0.43
     algunos
    0.43
     nombre
    0.43
     Namen
    0.43
    可能会
    0.43
     algumas
    0.42
    Act Density 0.007%

    No Known Activations