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

    Neuronpedia

    INDEX
    Explanations

    abstract art, designs, concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    1.22
    것
    1.20
     powied
    1.17
    }.
    1.04
    お
    1.03
     थक
    1.02
     어
    0.99
     않았
    0.97
    است
    0.97
    的相关
    0.94
    POSITIVE LOGITS
    i
    2.27
    ي
    1.59
    ة
    1.55
    י
    1.50
    in
    1.45
    يلا
    1.33
    ి
    1.32
    יים
    1.23
    t
    1.20
    يير
    1.19
    Act Density 0.069%

    No Known Activations