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

    Neuronpedia

    INDEX
    Explanations

    code configuration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dáng
    -0.06
    ورة
    -0.06
    myfile
    -0.06
    outfile
    -0.06
     mastur
    -0.06
    getRequest
    -0.06
     hồi
    -0.06
     طل
    -0.06
    .reverse
    -0.06
     수행
    -0.06
    POSITIVE LOGITS
    :bg
    0.07
    although
    0.07
    避
    0.07
     boğ
    0.07
    тє
    0.06
    (pic
    0.06
     常
    0.06
     consists
    0.06
     {@
    0.06
    >Contact
    0.06
    Act Density 0.001%

    No Known Activations