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

    Neuronpedia

    INDEX
    Explanations

    ultimate anti-selection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    म्ह
    0.46
    сне
    0.46
     oportunidades
    0.44
    TH
    0.44
    Firefox
    0.41
     confusión
    0.41
     Robson
    0.41
    ам
    0.40
    ทั้งหมด
    0.40
    HX
    0.40
    POSITIVE LOGITS
     BLUENRG
    0.53
     అంతే
    0.50
     क
    0.46
     노트
    0.45
     intestinal
    0.45
     attho
    0.45
    }_{+}\
    0.45
    រយៈ
    0.44
     冖
    0.44
     výstav
    0.43
    Act Density 0.000%

    No Known Activations