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

    Neuronpedia

    INDEX
    Explanations

    intense, requires, generates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Governor
    0.44
     Gubernur
    0.42
    ัก
    0.39
    dw
    0.39
     Nw
    0.38
     ভাবী
    0.38
     governor
    0.38
     Rad
    0.38
    연
    0.38
     Dw
    0.37
    POSITIVE LOGITS
    вовано
    0.43
     vatth
    0.41
     dilemmas
    0.39
     desempeño
    0.38
     заг
    0.38
     adore
    0.37
     чрезвы
    0.37
     extravag
    0.36
     зве
    0.36
     devenit
    0.36
    Act Density 0.001%

    No Known Activations