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

    Neuronpedia

    INDEX
    Explanations

    discussion, workshop, activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     olen
    0.37
     ennemis
    0.36
    rible
    0.36
    Когда
    0.35
    夊
    0.34
     ಯಾವಾಗ
    0.34
     školy
    0.33
     prolet
    0.33
     Schulen
    0.33
    มัน
    0.32
    POSITIVE LOGITS
     discussion
    0.69
     Discussion
    0.66
    讨论
    0.64
     discussions
    0.60
     Workshop
    0.59
     workshop
    0.59
    Discussion
    0.59
     discuss
    0.55
     обсу
    0.55
    discussion
    0.55
    Act Density 0.122%

    No Known Activations