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

    Neuronpedia

    INDEX
    Explanations

    company names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     /\.(
    -0.07
     aquí
    -0.07
    民主生活
    -0.07
     compare
    -0.07
     Эт
    -0.07
    ตาราง
    -0.07
     شكرا
    -0.07
    _MATRIX
    -0.07
    потен
    -0.07
    蔺
    -0.07
    POSITIVE LOGITS
     long
    0.07
     Amer
    0.07
     chimney
    0.06
     NSString
    0.06
    _OS
    0.06
     jong
    0.06
    道
    0.06
     Horn
    0.06
    veys
    0.06
    ombre
    0.06
    Act Density 0.078%

    No Known Activations