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

    Neuronpedia

    INDEX
    Explanations

    comments in code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     исслед
    -0.08
    ]);↵↵
    -0.08
     Kenntnisse
    -0.08
     시간
    -0.08
     pesquisadores
    -0.08
     phosphorus
    -0.07
    iril
    -0.07
     oste
    -0.07
     EXT
    -0.07
     গবেষ
    -0.07
    POSITIVE LOGITS
    ದೆ
    0.08
    氏
    0.08
    ¦
    0.08
     ස
    0.08
     �
    0.08
     共
    0.08
     �
    0.08
     njega
    0.08
    ходзіць
    0.08
    ेव
    0.08
    Act Density 0.000%

    No Known Activations