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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -Ch
    -0.08
    海
    -0.06
    .Matchers
    -0.06
    θεί
    -0.06
     Safety
    -0.06
    \Object
    -0.06
    Extent
    -0.06
    memory
    -0.06
    /TT
    -0.06
    DDL
    -0.06
    POSITIVE LOGITS
    μήμα
    0.07
     ）↵
    0.06
    italize
    0.06
    yc
    0.06
    ời
    0.06
    rit
    0.06
     porter
    0.06
     localized
    0.06
    Tbl
    0.06
    ้าอ
    0.06
    Act Density 0.008%

    No Known Activations