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

    Neuronpedia

    INDEX
    Explanations

    Website/quoted text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ăn
    -0.09
     timu
    -0.09
    atetime
    -0.08
     waqt
    -0.08
     saldo
    -0.08
    īn
    -0.08
    raa
    -0.08
    -camera
    -0.08
    줘
    -0.08
    /yyyy
    -0.07
    POSITIVE LOGITS
    <|reserved_200016|>
    0.11
    0.10
    0.10
     programmes
    0.09
    ]]>↵↵
    0.09
     blog
    0.08
    0.08
    0.08
     ]]>↵↵
    0.08
    .I
    0.08
    Act Density 0.713%
    No Known Activations