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

    Neuronpedia

    INDEX
    Explanations

    diverse text types

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ：“
    -0.07
     인증
    -0.06
     TRACE
    -0.06
     цик
    -0.06
    ]);
    -0.06
     улы
    -0.06
    ющими
    -0.06
    алася
    -0.06
    ynı
    -0.06
    olang
    -0.06
    POSITIVE LOGITS
     rss
    0.08
     lt
    0.07
     repealed
    0.07
    percent
    0.07
     amps
    0.06
    .mutable
    0.06
    say
    0.06
     Wilkinson
    0.06
    漫
    0.06
    �
    0.06
    Act Density 0.000%

    No Known Activations