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

    Neuronpedia

    INDEX
    Explanations

    unsure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    I
    0.48
     Krebs
    0.44
     তাকে
    0.43
     perspectivas
    0.42
    ı
    0.42
    㘟
    0.42
     Schmidt
    0.40
    צוני
    0.40
     pekerjaan
    0.40
    不幸
    0.40
    POSITIVE LOGITS
     unsure
    0.48
     safest
    0.44
     correct
    0.43
    otro
    0.42
     uncertain
    0.41
    餘
    0.41
    éder
    0.39
     correcta
    0.39
    負荷
    0.38
    رم
    0.38
    Act Density 0.011%

    No Known Activations