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

    Neuronpedia

    INDEX
    Explanations

    content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .”)
    0.46
    瑉
    0.42
    南部
    0.42
     Prefecture
    0.41
    lių
    0.41
    る
    0.40
    𝗹
    0.40
    ेंगू
    0.39
     Ngọc
    0.39
     Și
    0.39
    POSITIVE LOGITS
    ش
    0.63
    ir
    0.48
     d
    0.47
     broadcasts
    0.45
    avises
    0.45
    的基础
    0.44
     y
    0.44
     contenidos
    0.44
     rehearsals
    0.43
     activos
    0.43
    Act Density 0.045%

    No Known Activations