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

    Neuronpedia

    INDEX
    Explanations

    seeing and understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Мі
    0.17
    Ві
    0.16
     attuale
    0.16
    Фі
    0.15
    єю
    0.15
    website
    0.14
    نان
    0.14
     সেন্টার
    0.14
    àm
    0.14
    ινή
    0.14
    POSITIVE LOGITS
     it
    0.21
     them
    0.20
     some
    0.19
     people
    0.18
     something
    0.18
     beberapa
    0.17
     něco
    0.17
     banget
    0.17
     einige
    0.17
     약간
    0.17
    Act Density 0.338%

    No Known Activations