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

    Neuronpedia

    INDEX
    Explanations

    general subject or pronoun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     نیز
    1.52
     др
    1.47
    即可
    1.33
     จึง
    1.33
    จึง
    1.29
     также
    1.27
     jedoch
    1.25
    较为
    1.24
     dicha
    1.21
     Ainsi
    1.20
    POSITIVE LOGITS
     you
    1.25
     people
    1.23
     we
    1.21
     somebody
    1.19
     yeah
    1.17
     그러면은
    1.17
     everybody
    1.17
    একটা
    1.15
     একটা
    1.14
     cái
    1.12
    Act Density 0.022%

    No Known Activations