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

    Neuronpedia

    INDEX
    Explanations

    explanations and details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     உள்ள
    0.36
     सिक
    0.35
     connaissances
    0.35
     الإن
    0.35
     que
    0.34
    十大
    0.34
     Issues
    0.34
    urid
    0.34
     nods
    0.33
     Trit
    0.33
    POSITIVE LOGITS
    至于
    0.55
     acerca
    0.54
    关于
    0.52
     mengenai
    0.49
     HOW
    0.49
     किस
    0.47
    Exactly
    0.47
     tentang
    0.46
     ಯಾವ
    0.46
    至於
    0.46
    Act Density 0.085%

    No Known Activations