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

    Neuronpedia

    INDEX
    Explanations

    Code/technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    スク
    -0.09
     Nacht
    -0.06
     thankful
    -0.06
    -negative
    -0.06
     ajud
    -0.06
     velkou
    -0.06
     Рос
    -0.06
    icrous
    -0.06
     افت
    -0.06
    Democratic
    -0.06
    POSITIVE LOGITS
    د
    0.07
     WIDTH
    0.07
    """↵↵
    0.07
    MI
    0.06
    [D
    0.06
     ldc
    0.06
     웨
    0.06
    357
    0.06
    KL
    0.06
     vẻ
    0.06
    Act Density 0.000%

    No Known Activations