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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ICIAL
    -0.06
    -Nazi
    -0.06
    (rv
    -0.06
    mente
    -0.06
    ับผ
    -0.06
    ificados
    -0.06
    .destroyAllWindows
    -0.06
     cân
    -0.06
     secular
    -0.06
    -ste
    -0.06
    POSITIVE LOGITS
     nutrition
    0.08
    톤
    0.07
    ';↵
    0.07
    ";↵
    0.07
     dehydration
    0.06
    ].↵
    0.06
    ітет
    0.06
    輔
    0.06
    451
    0.06
     potassium
    0.06
    Act Density 0.020%

    No Known Activations