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

    Neuronpedia

    INDEX
    Explanations

    party

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     уровня
    -0.08
    _VERTEX
    -0.07
     Moss
    -0.07
     Plant
    -0.06
     copper
    -0.06
     CES
    -0.06
    upaten
    -0.06
     pois
    -0.06
    <typename
    -0.06
     cloak
    -0.06
    POSITIVE LOGITS
     parties
    0.07
    .isPlaying
    0.06
     Пет
    0.06
    表示
    0.06
    idental
    0.06
     Is
    0.06
    овый
    0.06
    (Module
    0.06
     [#
    0.06
     decoded
    0.06
    Act Density 0.026%

    No Known Activations