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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tester
    -0.07
     деся
    -0.06
    (chan
    -0.06
    ervlet
    -0.06
    alem
    -0.06
     labelText
    -0.06
    �
    -0.06
     Rod
    -0.06
    jango
    -0.06
    enet
    -0.06
    POSITIVE LOGITS
    ++){
↵
    0.07
     Employ
    0.07
    ="?
    0.07
    アメリカ
    0.06
    ergisi
    0.06
    $header
    0.06
     sayf
    0.06
    мів
    0.06
     افزار
    0.06
    .realm
    0.06
    Act Density 0.010%

    No Known Activations