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

    Neuronpedia

    INDEX
    Explanations

    complex tasks and specific content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ंजनों
    0.38
     ഓഫീ
    0.38
     кеңсеси
    0.37
     bridesmaid
    0.36
     refundable
    0.35
     кеңсесинде
    0.35
    हरादून
    0.34
     senior
    0.33
    adore
    0.33
     coordinadora
    0.33
    POSITIVE LOGITS
     wavy
    0.36
     ب
    0.35
    வன்
    0.34
     ח
    0.32
     qu
    0.32
     ق
    0.31
     q
    0.31
     в
    0.30
     d
    0.30
     prop
    0.30
    Act Density 5.802%

    No Known Activations