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

    Neuronpedia

    INDEX
    Explanations

    XML namespace attribute `xsi`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    غانستان
    0.53
    酸
    0.45
    复
    0.42
    ితో
    0.41
    ્યો
    0.41
     Certains
    0.41
     México
    0.40
    酷
    0.40
    改
    0.40
    斯的
    0.39
    POSITIVE LOGITS
    bari
    0.45
    freie
    0.45
    i
    0.44
    ansı
    0.43
    का
    0.42
    Sara
    0.42
     позволя
    0.42
    wari
    0.42
    freien
    0.41
    an
    0.41
    Act Density 0.001%

    No Known Activations