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

    Neuronpedia

    INDEX
    Explanations

    societal impact/structures/consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ر
    1.64
    ল
    1.31
     segu
    1.29
     awali
    1.26
     amely
    1.25
    stin
    1.24
    Chúc
    1.24
    ર
    1.23
     waktu
    1.23
    ꜱ
    1.20
    POSITIVE LOGITS
    '$
    1.40
    huge
    1.31
    ge
    1.28
    denly
    1.27
    niv
    1.26
    י
    1.23
    edges
    1.22
    ้
    1.22
    𝒆
    1.21
    سة
    1.19
    Act Density 0.028%

    No Known Activations