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

    Neuronpedia

    INDEX
    Explanations

    radical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    meni
    -0.06
     Ideally
    -0.06
    SECOND
    -0.06
    (src
    -0.06
     страны
    -0.06
    (D
    -0.06
    _G
    -0.06
    ourg
    -0.06
    冲
    -0.06
     Related
    -0.06
    POSITIVE LOGITS
    ظم
    0.07
    ל
    0.06
    専
    0.06
     aggression
    0.06
    });↵↵↵↵
    0.06
     employing
    0.06
     dysfunction
    0.06
     нія
    0.06
    graph
    0.06
    ولا
    0.06
    Act Density 0.001%

    No Known Activations