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

    Neuronpedia

    INDEX
    Explanations

    let and set operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    絶縁
    0.40
     रेट
    0.39
     இலவச
    0.37
     제시
    0.36
    𝖆
    0.36
    óso
    0.35
    inces
    0.35
    帏
    0.35
     manche
    0.35
    يكية
    0.34
    POSITIVE LOGITS
    dim
    0.43
    local
    0.40
    bitwise
    0.39
    Counts
    0.39
     Locals
    0.38
     locals
    0.37
    IntegerValue
    0.37
     tokens
    0.37
     counts
    0.37
     primitives
    0.36
    Act Density 0.002%

    No Known Activations