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

    Neuronpedia

    INDEX
    Explanations

    Q

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     исследования
    -0.07
    首席
    -0.06
     свобод
    -0.06
    感兴趣
    -0.06
     inert
    -0.06
     unanim
    -0.06
     sincere
    -0.06
     tearDown
    -0.06
    furt
    -0.06
    ◙
    -0.06
    POSITIVE LOGITS
     kutje
    0.09
     ()↵
    0.07
    죗
    0.07
    刀
    0.07
    XP
    0.07
     lia
    0.07
    "));↵
    0.07
    ).↵
    0.06
    饮用
    0.06
    脶
    0.06
    Act Density 0.002%

    No Known Activations