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

    Neuronpedia

    INDEX
    Explanations

    factor

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .math
    -0.07
    周期
    -0.07
    ="../../
    -0.07
    陌
    -0.07
    .Alignment
    -0.07
    景德
    -0.06
    大切な
    -0.06
    利用您的
    -0.06
     template
    -0.06
     наш
    -0.06
    POSITIVE LOGITS
     considerably
    0.07
     Beans
    0.07
     Rowe
    0.07
    劑
    0.07
    Posting
    0.07
     kidney
    0.07
    Square
    0.07
     riot
    0.06
     MACHINE
    0.06
    hoe
    0.06
    Act Density 0.001%

    No Known Activations