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

    Neuronpedia

    INDEX
    Explanations

    larger ranges or limits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     당신
    0.45
     以
    0.44
     प्रशासनिक
    0.43
     modernos
    0.43
     شما
    0.42
    互联网档案馆
    0.42
     వల్ల
    0.42
     you
    0.41
     orci
    0.41
    ləşdir
    0.41
    POSITIVE LOGITS
    on
    0.56
    c
    0.45
    ע
    0.44
    veno
    0.44
    Unter
    0.44
    vo
    0.43
    isko
    0.42
    othic
    0.42
    hits
    0.42
    onu
    0.42
    Act Density 0.000%

    No Known Activations