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

    Neuronpedia

    INDEX
    Explanations

    context-dependent instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    あるいは
    0.43
     యొక్క
    0.41
     কিংবা
    0.40
    <
    0.38
    或者
    0.38
    {\
    0.38
    能够
    0.37
     அவர்களுடைய
    0.37
    \'{
    0.35
    ütün
    0.35
    POSITIVE LOGITS
     ČR
    0.48
     الجميع
    0.46
     соц
    0.43
     অনেকে
    0.41
     devs
    0.40
     Kollegen
    0.39
     meski
    0.38
     זה
    0.38
     usato
    0.38
     priors
    0.38
    Act Density 0.954%

    No Known Activations