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

    Neuronpedia

    INDEX
    Explanations

    Rewatching/multiple viewings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     manifi
    -0.08
    ']['
    -0.07
    \":{\"
    -0.07
    ":{"
    -0.07
    рик
    -0.07
    ğin
    -0.07
    ли
    -0.07
     continuidad
    -0.07
     나타
    -0.07
    ѓ
    -0.07
    POSITIVE LOGITS
     rere
    0.10
     반복
    0.10
    重复
    0.09
     repetir
    0.09
     повтор
    0.09
     熟
    0.09
     revisit
    0.09
     mehrfach
    0.09
     repeated
    0.09
    _repeat
    0.09
    Act Density 0.027%

    No Known Activations