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

    Neuronpedia

    INDEX
    Explanations

    language prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    साठी
    0.80
     fără
    0.69
    ಗಾಗಿ
    0.67
    extérieur
    0.66
    šanas
    0.66
     kvůli
    0.66
    tumblr
    0.64
     بسرعة
    0.64
    για
    0.64
    даг
    0.63
    POSITIVE LOGITS
     in
    1.28
     trong
    1.21
    ใน
    1.20
     dalam
    1.19
     ใน
    1.01
     katika
    0.99
     في
    0.98
     în
    0.93
     nelle
    0.89
     в
    0.86
    Act Density 0.000%

    No Known Activations