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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (ticket
    -0.07
     dataList
    -0.07
    プロ
    -0.07
     mansion
    -0.07
     upd
    -0.07
    )))↵↵↵
    -0.06
    rt
    -0.06
     Driver
    -0.06
     배열
    -0.06
     Rao
    -0.06
    POSITIVE LOGITS
    عد
    0.07
    戰
    0.06
    .springframework
    0.06
    ovalo
    0.06
    سبب
    0.06
     uphe
    0.06
    boa
    0.06
    ondere
    0.06
    ेकर
    0.06
    ansi
    0.06
    Act Density 0.053%

    No Known Activations