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

    Neuronpedia

    INDEX
    Explanations

    rum

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wszyst
    -0.07
    땅
    -0.07
    ptrdiff
    -0.07
     bilder
    -0.06
     Inches
    -0.06
     �
    -0.06
    要闻
    -0.06
     הדברים
    -0.06
    重要指示
    -0.06
    (before
    -0.06
    POSITIVE LOGITS
    =#{
    0.08
    IV
    0.07
    ({
    0.07
    万个
    0.07
    CTest
    0.07
    .foo
    0.07
    就把
    0.07
     })
↵
↵
    0.07
    月底
    0.07
    (pr
    0.07
    Act Density 0.051%

    No Known Activations